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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and their associated concepts or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vital
    -0.15
    GIN
    -0.15
     Vital
    -0.14
    raman
    -0.14
    lee
    -0.14
    kaar
    -0.14
     shoe
    -0.14
    anium
    -0.14
    estr
    -0.14
    amen
    -0.14
    POSITIVE LOGITS
    ëĭ´
    0.16
    /bus
    0.16
    luet
    0.15
    OTTOM
    0.15
    ylland
    0.15
    èĬĻ
    0.15
    orne
    0.15
    аÑĢÑĮ
    0.14
    ÑĥÑĪка
    0.14
    amil
    0.14
    Act Density 0.005%

    No Known Activations