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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or personalities

    oai_token-act-pair · gpt-3.5-turbo

    proper names of individuals, particularly those referenced in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sexual
    -0.69
     excludes
    -0.68
     impair
    -0.63
     fulfilling
    -0.61
     conformity
    -0.61
     grooming
    -0.59
    tumblr
    -0.59
     hath
    -0.58
     derailed
    -0.58
     damaged
    -0.57
    POSITIVE LOGITS
    è¦ļéĨĴ
    0.78
    veland
    0.75
     sarcast
    0.75
     Ital
    0.74
     gloom
    0.73
    ¿½
    0.72
     rhet
    0.72
    Ĭ±
    0.68
     Azerb
    0.67
    anca
    0.67
    Act Density 0.282%

    No Known Activations