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

    Neuronpedia

    INDEX
    Explanations

    locations or venues

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to formal events, organizations, or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.65
    bal
    -0.60
    condition
    -0.60
    Balance
    -0.60
    tein
    -0.59
    TYPE
    -0.59
    scape
    -0.58
    âĸ¬
    -0.57
     population
    -0.57
    Otherwise
    -0.56
    POSITIVE LOGITS
    uggest
    1.21
    hip
    1.15
    heet
    1.11
    chool
    1.11
    hips
    1.10
    poons
    1.10
    creen
    1.10
    mith
    1.07
    paces
    1.06
    hots
    1.03
    Act Density 0.653%

    No Known Activations