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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making adjustments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chest
    -0.16
    anke
    -0.16
    ensa
    -0.15
    isci
    -0.15
    osemite
    -0.15
    ORIZONTAL
    -0.14
    aver
    -0.14
    _tokenize
    -0.14
    ograd
    -0.13
    agedList
    -0.13
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.17
    ments
    0.17
    aland
    0.15
    /update
    0.15
    lef
    0.15
    /rem
    0.14
     Tactics
    0.14
    /control
    0.14
    avad
    0.14
    emean
    0.14
    Act Density 0.028%

    No Known Activations