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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making sense or being meaningful

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

    phrases that express the concept of making a difference or sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.22
    3:0.08
    4:0.04
    5:0.05
    6:0.01
    7:0.06
    8:0.20
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
    anwhile
    -1.11
     Pigs
    -1.03
    rought
    -1.00
    stration
    -0.97
    planes
    -0.97
    idth
    -0.95
     Boo
    -0.93
     initiated
    -0.93
     faithfully
    -0.92
     Badge
    -0.91
    POSITIVE LOGITS
    Wan
    1.49
    kish
    1.33
    �
    1.21
    undo
    1.20
    sense
    1.20
    ˈ
    1.19
     dent
    1.11
    _-_
    1.08
    Package
    1.07
    pmwiki
    1.07
    Act Density 0.201%

    No Known Activations