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

    Neuronpedia

    INDEX
    Explanations

    topical trends and events likely from online platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trending topics and social discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.70
    otos
    -0.67
    votes
    -0.67
    Frames
    -0.65
    luent
    -0.64
    Specific
    -0.63
    ãĥĥ
    -0.60
    times
    -0.59
     tranquil
    -0.59
    NOR
    -0.58
    POSITIVE LOGITS
    heet
    1.69
    mith
    1.46
    hip
    1.46
    ystem
    1.41
    creen
    1.40
    cale
    1.37
    erver
    1.36
    pace
    1.34
    cape
    1.31
    hift
    1.27
    Act Density 0.518%

    No Known Activations