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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of reluctance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efs
    -0.17
    els
    -0.16
     IP
    -0.15
    eeper
    -0.15
    oun
    -0.15
    豪
    -0.15
    224
    -0.14
    eph
    -0.14
    licit
    -0.14
    egers
    -0.14
    POSITIVE LOGITS
    azzi
    0.17
    GORITH
    0.15
    umatic
    0.15
    _regularizer
    0.14
    _learn
    0.14
    VS
    0.14
    ancellor
    0.14
    igmatic
    0.14
    .dtd
    0.14
    brick
    0.14
    Act Density 0.529%

    No Known Activations