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

    Neuronpedia

    INDEX
    Explanations

    themes of influence, surprise, fun, and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    much + descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oflavin
    -0.57
    elett
    -0.46
    Ży
    -0.45
    idu
    -0.44
    WARE
    -0.43
    sapat
    -0.43
    maus
    -0.42
    ivar
    -0.41
    PLATES
    -0.41
     asf
    -0.41
    POSITIVE LOGITS
     much
    0.59
    MeasureSpec
    0.57
    Much
    0.54
     Much
    0.53
    much
    0.48
     mye
    0.45
     mucho
    0.44
     MUCH
    0.42
    GenerationType
    0.41
    postsleuth
    0.41
    Act Density 0.022%

    No Known Activations