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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    elements related to rankings and hierarchical positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γ
    -0.82
    avan
    -0.80
     interf
    -0.72
    react
    -0.71
    auga
    -0.69
    displayText
    -0.69
    iaz
    -0.69
    storms
    -0.67
    hran
    -0.66
    anol
    -0.65
    POSITIVE LOGITS
     Top
    2.04
     top
    1.87
     TOP
    1.82
    Top
    1.76
    TOP
    1.65
     ranking
    1.62
    top
    1.62
     ranked
    1.59
     Bottom
    1.53
     rankings
    1.50
    Act Density 0.253%

    No Known Activations