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

    Neuronpedia

    INDEX
    Explanations

    words associated with upward and downward movement or changes in position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fav
    -0.17
    essional
    -0.16
     Randall
    -0.15
    laus
    -0.14
    feb
    -0.14
    stÃŃ
    -0.14
    aceous
    -0.13
    ongoose
    -0.13
    fü
    -0.13
    leston
    -0.13
    POSITIVE LOGITS
    -desc
    0.19
    ion
    0.17
    endez
    0.17
    orp
    0.17
    ents
    0.16
    antly
    0.16
    mal
    0.16
    ior
    0.15
    ally
    0.15
    ence
    0.15
    Act Density 0.042%

    No Known Activations