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

    Neuronpedia

    INDEX
    Explanations

    terms related to racism

    oai_token-act-pair · gpt-3.5-turbo

    discourse related to racism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TAIN
    -0.82
    ITNESS
    -0.67
    arters
    -0.63
    cise
    -0.61
     Expend
    -0.61
    OPER
    -0.60
     RPM
    -0.60
     abort
    -0.59
    icles
    -0.59
     rpm
    -0.59
    POSITIVE LOGITS
     prejudice
    1.05
    ophobia
    0.92
    ophobic
    0.90
     perv
    0.84
    itism
    0.81
     rife
    0.79
     worsened
    0.76
     prejud
    0.76
     rampant
    0.75
     racism
    0.75
    Act Density 0.039%

    No Known Activations