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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that specify factors or contexts influencing a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bust
    -0.17
    urf
    -0.17
    kova
    -0.15
    zek
    -0.15
    ware
    -0.15
    GP
    -0.14
    ady
    -0.14
    kou
    -0.14
    ìľ¨
    -0.14
    hood
    -0.14
    POSITIVE LOGITS
     whether
    0.22
    whether
    0.18
     upon
    0.16
     circumstances
    0.16
     depending
    0.15
    æĺ¯åIJ¦
    0.15
    avad
    0.15
    jed
    0.15
    Whether
    0.15
    FFT
    0.15
    Act Density 0.014%

    No Known Activations