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

    Neuronpedia

    INDEX
    Explanations

    expressions of fascination or interest in various subjects

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

    fascinating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.62
    帖最后由
    -0.59
     '\\;'
    -0.58
    Condol
    -0.57
     Audiodateien
    -0.57
    -0.57
    AsUp
    -0.57
    twimg
    -0.54
    verwijspagina
    -0.52
    Shoes
    -0.52
    POSITIVE LOGITS
     fascinating
    1.02
     fascinated
    0.92
     fascination
    0.89
     fascin
    0.81
    cinating
    0.81
     faszin
    0.69
     Fas
    0.66
    CardContent
    0.59
     Fantastic
    0.58
    fantastic
    0.58
    Act Density 0.003%

    No Known Activations