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

    Neuronpedia

    INDEX
    Explanations

    expressions related to coping mechanisms and positive distractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omain
    -0.15
     genu
    -0.14
    -generic
    -0.14
     thrill
    -0.14
    ll
    -0.14
    untas
    -0.14
     blackmail
    -0.14
    marks
    -0.13
     bek
    -0.13
    loo
    -0.13
    POSITIVE LOGITS
    yonel
    0.17
    annes
    0.15
    gart
    0.15
    vise
    0.15
     tÆ°Æ¡i
    0.15
    ropy
    0.14
    Unchecked
    0.14
    νά
    0.14
    º«
    0.14
    PageRoute
    0.14
    Act Density 0.251%

    No Known Activations