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

    Neuronpedia

    INDEX
    Explanations

    objects or items being carried by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of potential violations or illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.80
    osaurus
    -0.77
    ouble
    -0.76
    inois
    -0.73
    uto
    -0.71
    ername
    -0.70
    oreal
    -0.69
     XIII
    -0.66
    dit
    -0.64
    folio
    -0.64
    POSITIVE LOGITS
    è¦ļéĨĴ
    0.74
     Jury
    0.66
    wash
    0.61
    SOURCE
    0.61
    ³³³
    0.60
    accompan
    0.60
    ·
    0.59
    ³³
    0.59
     Said
    0.56
    jer
    0.56
    Act Density 0.154%

    No Known Activations