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

    Neuronpedia

    INDEX
    Explanations

    terms related to adding or including elements, particularly in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    routeProvider
    -0.35
     comples
    -0.34
     flattered
    -0.33
    並
    -0.33
     Gottes
    -0.32
     نار
    -0.31
    危險
    -0.31
    危险
    -0.31
     Seems
    -0.30
    onBackPressed
    -0.30
    POSITIVE LOGITS
     незавершена
    0.65
     additive
    0.61
    offsetof
    0.61
     additions
    0.60
     aggi
    0.59
    Positive
    0.59
    httphttps
    0.59
    __);
    0.59
    ValueStyle
    0.59
    Added
    0.57
    Act Density 1.774%

    No Known Activations