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

    Neuronpedia

    INDEX
    Explanations

    the presence of phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.09
    3:0.18
    4:0.01
    5:0.03
    6:0.05
    7:0.10
    8:0.06
    9:0.22
    10:0.07
    11:0.10
    Negative Logits
    idays
    -1.21
    isen
    -1.15
    hai
    -1.15
    zees
    -1.13
    rite
    -1.11
    seekers
    -1.10
     Fever
    -1.09
    mentioned
    -1.09
    items
    -1.08
    parts
    -1.08
    POSITIVE LOGITS
     corrid
    1.20
     optimal
    1.17
    LOCK
    1.17
     Mata
    1.15
     destro
    1.14
    ertodd
    1.12
     unorthodox
    1.11
     proprietary
    1.09
     niche
    1.06
     withd
    1.03
    Act Density 0.019%

    No Known Activations