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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approximate numerical values or estimates

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ation
    -0.75
    ged
    -0.65
    pon
    -0.65
    (')
    -0.65
    king
    -0.63
    ither
    -0.63
    ля
    -0.63
    ed
    -0.60
    υ
    -0.60
    ar
    -0.59
    POSITIVE LOGITS
    approximately
    1.01
     approximately
    0.97
    picable
    0.96
    ximately
    0.94
     saites
    0.93
    Approximately
    0.92
     Approximately
    0.91
    SourceChecksum
    0.91
    applicant
    0.90
    issory
    0.87
    Act Density 0.007%

    No Known Activations