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

    Neuronpedia

    INDEX
    Explanations

    references to clowns or comedic characters

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

    clowns and fools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -1.09
    AccessorTable
    -0.64
    Παραπομπές
    -0.60
     nahilalakip
    -0.59
     Infórmanos
    -0.58
    OGND
    -0.57
    xchange
    -0.56
    RegressionTest
    -0.55
    momix
    -0.55
     kiệm
    -0.54
    POSITIVE LOGITS
     Clown
    1.23
    Clown
    1.19
     clown
    1.13
    clown
    1.05
     clowns
    1.04
    lowns
    0.94
     Clow
    0.84
    🤡
    0.79
     palha
    0.59
     laughter
    0.55
    Act Density 0.006%

    No Known Activations