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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "man."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rez
    -0.16
    alars
    -0.16
    ts
    -0.16
    gor
    -0.16
    à¸ļà¸ģ
    -0.14
    ügen
    -0.14
    ossal
    -0.14
    idan
    -0.14
    genic
    -0.14
    /lic
    -0.14
    POSITIVE LOGITS
    hattan
    0.29
    agements
    0.29
    tras
    0.28
    agment
    0.26
    iscal
    0.25
    fred
    0.24
    chester
    0.24
    orial
    0.23
    handled
    0.23
    ifold
    0.23
    Act Density 0.037%

    No Known Activations