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

    Neuronpedia

    INDEX
    Explanations

    references to subscribing to receive daily news

    oai_token-act-pair · gpt-3.5-turbo

    the most significant or prominent stories in news and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tif
    -0.77
    zek
    -0.70
    heid
    -0.67
     Leban
    -0.67
    ategories
    -0.66
    wat
    -0.66
    æ©
    -0.65
    ricks
    -0.63
    Þ
    -0.63
     citiz
    -0.63
    POSITIVE LOGITS
     possible
    1.01
     bang
    0.96
    liest
    0.92
     amount
    0.76
     practicable
    0.74
     version
    0.74
    hest
    0.74
    iest
    0.73
     conceivable
    0.72
     imaginable
    0.70
    Act Density 0.092%

    No Known Activations