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

    Neuronpedia

    INDEX
    Explanations

    words related to gamma rays and the activity of blackmailing

    oai_token-act-pair · gpt-3.5-turbo

    references to gamma rays and instances of blackmail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onso
    -0.82
    Ĵ
    -0.82
    iners
    -0.82
    icably
    -0.81
    votes
    -0.80
    asca
    -0.78
    ivities
    -0.77
    actus
    -0.76
    ouston
    -0.76
    ires
    -0.73
    POSITIVE LOGITS
     Rabbit
    0.85
    CHQ
    0.73
     Joker
    0.70
     Roh
    0.68
     Moody
    0.67
     SV
    0.66
     Krug
    0.66
     broccoli
    0.65
     Penguin
    0.65
     caul
    0.65
    Act Density 0.021%

    No Known Activations