Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentence fragments from technology-related texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "since" in various contexts related to time or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.01
    2:0.07
    3:0.15
    4:0.03
    5:0.15
    6:0.04
    7:0.07
    8:0.10
    9:0.03
    10:0.14
    11:0.07
    Negative Logits
    gently
    -0.95
    vant
    -0.95
    BILITIES
    -0.91
    UGC
    -0.91
    ettings
    -0.87
    lon
    -0.87
    rette
    -0.86
    ettes
    -0.84
    Topic
    -0.84
    ilet
    -0.83
    POSITIVE LOGITS
    cember
    1.03
     inception
    0.92
    ynthesis
    0.91
     failed
    0.86
    terday
    0.84
     overth
    0.84
     mysteriously
    0.82
     previous
    0.80
     hail
    0.79
     bowed
    0.79
    Act Density 0.133%

    No Known Activations