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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements that include quotes or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Developer
    -0.69
     behold
    -0.69
     giveaway
    -0.62
     Initi
    -0.60
     Lesbian
    -0.59
     Crusader
    -0.58
    JECT
    -0.56
     cradle
    -0.56
     earliest
    -0.56
    alter
    -0.55
    POSITIVE LOGITS
    ãĤª
    0.78
    nces
    0.77
    */(
    0.75
    itely
    0.72
    xual
    0.69
    leeve
    0.68
    icy
    0.68
    iband
    0.67
    henko
    0.67
    ayers
    0.67
    Act Density 0.138%

    No Known Activations