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

    Neuronpedia

    INDEX
    Explanations

    references to human characteristics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esp
    -0.17
    iž
    -0.15
     Magnum
    -0.15
    odore
    -0.14
    _ulong
    -0.14
    abox
    -0.14
    ви
    -0.14
     anders
    -0.14
     stocks
    -0.14
    اÛĮد
    -0.14
    POSITIVE LOGITS
    olvable
    0.16
    udent
    0.15
    active
    0.15
    ä¹¾
    0.14
    ãģĭãĤĬ
    0.14
    rang
    0.13
    ãĥ³ãĥĸ
    0.13
    \""
    0.13
    eyh
    0.13
    gar
    0.13
    Act Density 0.213%

    No Known Activations