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

    Neuronpedia

    INDEX
    Explanations

    references to global and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afone
    -0.17
    ruba
    -0.16
    uristic
    -0.15
    strup
    -0.15
     влад
    -0.14
    ifo
    -0.14
    akit
    -0.14
    837
    -0.14
    ulet
    -0.14
    odings
    -0.14
    POSITIVE LOGITS
    -wide
    0.23
     itself
    0.22
    wide
    0.20
     experienced
    0.17
     overall
    0.16
     collectively
    0.16
    isti
    0.16
     wide
    0.15
    /system
    0.15
     te
    0.15
    Act Density 0.126%

    No Known Activations