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

    Neuronpedia

    INDEX
    Explanations

    references to personal attire and appearance within a customer service context

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

    ensure that

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects descriptions of a person’s clothing and physical appearance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     matéria
    -0.38
     mundane
    -0.37
     ...
    -0.35
    radan
    -0.35
     Silverman
    -0.35
     Huxley
    -0.35
     sogni
    -0.35
    pruch
    -0.35
    ijen
    -0.34
     nasze
    -0.34
    POSITIVE LOGITS
     ब्रेकडाउन
    0.84
     defaultstate
    0.73
    principalColumn
    0.72
     незавершена
    0.67
     Infórmanos
    0.66
     iprot
    0.63
     للمعارف
    0.62
     كومونز
    0.61
    writeFieldEnd
    0.60
    MigrationBuilder
    0.59
    Act Density 0.115%

    No Known Activations