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

    Neuronpedia

    INDEX
    Explanations

    numbers related to scores or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring or points in competitive scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.77
    uthor
    -0.77
    anical
    -0.72
    LECT
    -0.72
    ourt
    -0.72
    yss
    -0.72
    annis
    -0.71
     Romeo
    -0.71
     externalToEVAOnly
    -0.69
    ctors
    -0.67
    POSITIVE LOGITS
    manship
    0.93
    ifications
    0.83
    blank
    0.75
     points
    0.75
    uing
    0.73
    points
    0.72
     blank
    0.72
     Reyes
    0.71
    point
    0.71
    ense
    0.70
    Act Density 0.027%

    No Known Activations