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

    Neuronpedia

    INDEX
    Explanations

    words related to cultural elements and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.09
    ,
    -0.95
     (
    -0.85
     -
    -0.83
    .
    -0.82
    :
    -0.80
     in
    -0.80
    -
    -0.79
    ↵
    -0.77
     and
    -0.75
    POSITIVE LOGITS
     Efq
    1.82
     myſelf
    1.67
     ་་
    1.66
     ―――――
    1.61
     Anſ
    1.60
     ſind
    1.60
     itſelf
    1.54
    ſelf
    1.50
     Houſe
    1.49
     Theſe
    1.49
    Act Density 0.011%

    No Known Activations