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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "strike" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilton
    -0.17
    esta
    -0.16
    ucci
    -0.16
    ekil
    -0.15
    igned
    -0.15
    woke
    -0.15
    wig
    -0.15
    rias
    -0.14
     Platt
    -0.14
    rians
    -0.14
    POSITIVE LOGITS
    out
    0.17
    -through
    0.15
    alim
    0.15
    outs
    0.15
    AGE
    0.15
    age
    0.14
    eres
    0.14
    kus
    0.14
    опиÑģ
    0.14
    aldi
    0.14
    Act Density 0.017%

    No Known Activations