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

    Neuronpedia

    INDEX
    Explanations

    various forms of stereotypes

    oai_token-act-pair · gpt-3.5-turbo

    references to stereotypes and myths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.80
    ateur
    -0.77
    ayan
    -0.75
    sterdam
    -0.74
    rique
    -0.72
    Sync
    -0.68
    undred
    -0.66
    ighth
    -0.66
    hner
    -0.66
    ucha
    -0.65
    POSITIVE LOGITS
     stereotyp
    0.98
     stereotype
    0.89
     stereotypes
    0.89
     notions
    0.81
    è¦ļéĨĴ
    0.81
     clich
    0.78
     msec
    0.73
     depictions
    0.73
     portray
    0.73
     Monstrous
    0.71
    Act Density 0.047%

    No Known Activations