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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically related to individuals or companies

    oai_token-act-pair · gpt-3.5-turbo

    individual letters, particularly those appearing frequently in names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.79
    omaly
    -0.70
     anonymity
    -0.65
     hostages
    -0.63
     wrath
    -0.63
    Ĥİ
    -0.62
    ĺħ
    -0.62
     privacy
    -0.60
    ģ«
    -0.60
     plutonium
    -0.60
    POSITIVE LOGITS
    inki
    0.80
    akeru
    0.79
    achus
    0.75
    learning
    0.72
    vec
    0.71
    oys
    0.71
    eret
    0.70
    Tal
    0.69
    initialized
    0.69
    oku
    0.69
    Act Density 0.082%

    No Known Activations