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

    Neuronpedia

    INDEX
    Explanations

    instructions or guidance related to specific actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming or strategy-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Krish
    -0.63
    paralle
    -0.62
    inen
    -0.55
    ibur
    -0.54
     solved
    -0.53
     horr
    -0.52
    ican
    -0.52
    ¶ħ
    -0.51
    never
    -0.50
     Hindus
    -0.50
    POSITIVE LOGITS
    uberty
    0.66
    )).
    0.66
    robe
    0.62
    swing
    0.58
    pection
    0.58
    pport
    0.58
    attr
    0.58
    enium
    0.57
    uly
    0.57
     VIDEOS
    0.57
    Act Density 0.935%

    No Known Activations