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

    Neuronpedia

    INDEX
    Explanations

    casual expressions and informal language used in personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    十分的
    -0.32
     avrebbero
    -0.27
    に
    -0.25
    estacks
    -0.25
     hereof
    -0.23
     apprehensions
    -0.23
     vital
    -0.23
     pungkas
    -0.23
     jelasnya
    -0.23
     endeavours
    -0.22
    POSITIVE LOGITS
     purpoſe
    0.80
    RenderAtEndOf
    0.77
     dunno
    0.75
     Reſ
    0.73
     myſelf
    0.71
     Diſ
    0.70
    Personendaten
    0.70
    addContainerGap
    0.69
    Cyfeiriadau
    0.69
    Билгалдахарш
    0.66
    Act Density 0.343%

    No Known Activations