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

    Neuronpedia

    INDEX
    Explanations

    numbers with some level of significance

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coch
    -0.69
     Faul
    -0.63
     ag
    -0.61
     Briggs
    -0.60
     Hawth
    -0.59
     Boyd
    -0.58
     Ag
    -0.56
     Clint
    -0.55
     Gat
    -0.55
     Cannon
    -0.54
    POSITIVE LOGITS
    âĢ²
    0.70
     ILCS
    0.69
    ourney
    0.69
     consecutive
    0.65
     Reasons
    0.62
    utenberg
    0.61
     disparate
    0.61
     devote
    0.60
    %-
    0.60
    dfx
    0.60
    Act Density 0.207%

    No Known Activations