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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fascinating."

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

    fascinating and intriguing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.53
    ImageIO
    -0.52
    Condol
    -0.51
    OGND
    -0.47
     tricycle
    -0.46
    SOUNDBITE
    -0.44
     cloths
    -0.43
    LPD
    -0.43
    Medic
    -0.43
    VYMaps
    -0.43
    POSITIVE LOGITS
     fascinating
    1.88
    cinating
    1.38
     intriguing
    1.12
     faszin
    1.02
     interesting
    0.91
     fantastic
    0.90
     fascin
    0.85
     wonderful
    0.84
     encantador
    0.84
     exciting
    0.83
    Act Density 0.003%

    No Known Activations