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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific numbers or quantities

    oai_token-act-pair · gpt-3.5-turbo

    colons indicating lists or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.76
     equivalents
    -0.62
    emed
    -0.59
    istas
    -0.59
    terday
    -0.58
    ista
    -0.58
    izons
    -0.56
    lar
    -0.56
    ento
    -0.55
    ,
    -0.55
    POSITIVE LOGITS
     namely
    1.60
     That
    0.98
     Firstly
    0.95
     Its
    0.92
     Whether
    0.90
     Their
    0.88
     They
    0.83
     Getting
    0.81
     Bringing
    0.77
     Creating
    0.77
    Act Density 0.145%

    No Known Activations