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

    Neuronpedia

    INDEX
    Explanations

    references to sexism and harassment

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

    sexism, harassment, and homophobia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urlencoded
    -0.50
    SystemColors
    -0.46
    WaitGroup
    -0.45
    PerformLayout
    -0.45
     consciousness
    -0.45
     Malden
    -0.45
    AutoScaleMode
    -0.44
     SqlConnection
    -0.44
    السكان
    -0.44
     Moreau
    -0.43
    POSITIVE LOGITS
     sexism
    1.57
     sexist
    1.55
    ogyn
    0.93
     superstitious
    0.63
     chau
    0.62
    fjspx
    0.62
     superstitions
    0.61
    ogy
    0.59
     unfair
    0.58
     homophobic
    0.57
    Act Density 0.006%

    No Known Activations