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

    Neuronpedia

    INDEX
    Explanations

    the word "Anyone" and its variations, indicating a search for inclusive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iger
    -0.67
    urations
    -0.65
     Hound
    -0.65
    bows
    -0.65
     Resurrection
    -0.63
    rament
    -0.63
    irth
    -0.63
    ocamp
    -0.63
    tnc
    -0.63
    ories
    -0.62
    POSITIVE LOGITS
     else
    1.76
    else
    1.33
     Else
    1.24
    Else
    1.21
     who
    1.02
     wishing
    0.96
    who
    0.95
     subscribed
    0.93
     interested
    0.93
    soever
    0.89
    Act Density 0.033%

    No Known Activations