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

    Neuronpedia

    INDEX
    Explanations

    variances or changes in quantity, likely represented by mathematical operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bu
    -0.56
    tvguidetime
    -0.56
    ...
    -0.53
     -
    -0.52
     imp
    -0.51
    bus
    -0.50
    imp
    -0.50
    зни
    -0.49
    my
    -0.49
     Numerology
    -0.49
    POSITIVE LOGITS
     Cæsar
    0.71
     betweenstory
    0.67
     isComment
    0.67
     (\<
    0.65
    ^(@)
    0.65
     ―――――
    0.64
     photolibrary
    0.63
     Inflate
    0.62
    TokenNameLBRACE
    0.62
     iſt
    0.60
    Act Density 0.016%

    No Known Activations