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

    Neuronpedia

    INDEX
    Explanations

    descriptions of architectural structures and features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture and structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALLY
    -0.72
    football
    -0.68
    Hur
    -0.65
    KNOWN
    -0.63
     acquaintance
    -0.63
    ties
    -0.63
    Attempts
    -0.61
    BAT
    -0.61
     Democrat
    -0.58
    BUG
    -0.57
    POSITIVE LOGITS
    paces
    1.46
    mith
    1.43
    pace
    1.42
    hips
    1.39
    poons
    1.30
    hip
    1.22
    etting
    1.20
    ongs
    1.15
    hare
    1.14
    pring
    1.14
    Act Density 0.262%

    No Known Activations