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

    Neuronpedia

    INDEX
    Explanations

    terms associated with enlightenment and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asting
    -0.17
    ihn
    -0.16
    омеÑĢ
    -0.16
    ÑĩаÑģ
    -0.15
    .Atomic
    -0.15
     BOTTOM
    -0.15
    panic
    -0.15
    arding
    -0.14
    /us
    -0.14
    elling
    -0.14
    POSITIVE LOGITS
    .wikipedia
    0.25
    GLISH
    0.22
    igma
    0.22
    rico
    0.21
    abler
    0.20
    viron
    0.20
     route
    0.20
    igmatic
    0.19
    yclopedia
    0.19
    sched
    0.18
    Act Density 0.024%

    No Known Activations