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

    Neuronpedia

    INDEX
    Explanations

    indicators of a change in conversational context or topic shift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.47
    atta
    -0.46
    attached
    -0.40
    odes
    -0.40
     Suck
    -0.38
    ode
    -0.37
    beu
    -0.37
    race
    -0.37
    IVEREF
    -0.37
    jsdelivr
    -0.37
    POSITIVE LOGITS
     beginnetje
    0.55
     <=",
    0.54
    期刊论文
    0.50
     ویکی‌پدی
    0.46
    ➟
    0.46
    setVerticalGroup
    0.45
     TestBed
    0.41
    &__
    0.41
     Normdatei
    0.40
    rrggbb
    0.39
    Act Density 0.000%

    No Known Activations