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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "all" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TEGER
    -0.15
    woke
    -0.15
    çĶļèĩ³
    -0.15
    cente
    -0.14
    erras
    -0.14
    à¹Ĥย
    -0.14
    amus
    -0.14
    åĨĮ
    -0.14
    ocate
    -0.14
    quirer
    -0.13
    POSITIVE LOGITS
     throughout
    0.28
     along
    0.27
     bets
    0.25
     across
    0.25
     through
    0.24
     indications
    0.23
     anybody
    0.23
     eyes
    0.23
     hell
    0.23
     anyone
    0.23
    Act Density 0.053%

    No Known Activations