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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific numbers and financial values

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve positions or relationships relative to 'at' and variations of directional or locational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Judd
    -0.63
     Cosmos
    -0.58
     Crimson
    -0.58
     forth
    -0.57
     Franks
    -0.56
     Abrams
    -0.55
     dyn
    -0.55
     Quart
    -0.54
     Chao
    -0.53
    ÃŁ
    -0.53
    POSITIVE LOGITS
    risk
    0.92
    mast
    0.91
    antage
    0.77
    large
    0.75
     expense
    0.75
    point
    0.75
     discretion
    0.74
     outset
    0.71
    hak
    0.71
     mast
    0.70
    Act Density 0.045%

    No Known Activations