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

    Neuronpedia

    INDEX
    Explanations

    terms related to reversal or invalidation of decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unik
    -0.15
    è¦ļ
    -0.15
    ponge
    -0.14
    oku
    -0.14
    urm
    -0.14
    vision
    -0.14
    vise
    -0.14
    istic
    -0.14
     Replay
    -0.14
    uld
    -0.14
    POSITIVE LOGITS
    ingham
    0.17
    inia
    0.16
    ailer
    0.16
    ingo
    0.15
    rush
    0.15
     οÏħ
    0.15
    EGIN
    0.15
    IU
    0.14
    lep
    0.14
    460
    0.14
    Act Density 0.003%

    No Known Activations