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

    Neuronpedia

    INDEX
    Explanations

    sections of text that are empty or contain placeholder content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     useEffect
    -0.54
    Дереккөздер
    -0.52
     ubic
    -0.52
    itude
    -0.51
    decine
    -0.50
     tặng
    -0.50
    (&$
    -0.48
    addGroup
    -0.48
    behaviors
    -0.48
    rijfs
    -0.48
    POSITIVE LOGITS
    blank
    0.77
     blanks
    0.76
     auffi
    0.71
     babies
    0.71
     Babies
    0.71
     signing
    0.69
     signer
    0.68
     bankers
    0.67
     blank
    0.67
     Banker
    0.67
    Act Density 0.043%

    No Known Activations