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

    Neuronpedia

    INDEX
    Explanations

    words related to irregularity or illegality

    oai_token-act-pair · gpt-3.5-turbo

    references to irregularities and illegality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canterbury
    -0.68
     Copenhagen
    -0.65
    ogie
    -0.65
     mantra
    -0.62
     Omaha
    -0.60
     observation
    -0.59
     Jac
    -0.58
    ³³³³³³³³³³³³³³³³
    -0.57
    ãĤ´ãĥ³
    -0.57
     parental
    -0.56
    POSITIVE LOGITS
    iates
    0.85
    iour
    0.84
    ious
    0.81
    itives
    0.80
    INESS
    0.80
    ially
    0.77
    rants
    0.76
    iating
    0.76
    IAL
    0.75
    iated
    0.75
    Act Density 0.042%

    No Known Activations