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

    Neuronpedia

    INDEX
    Explanations

    references to work and labor-related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enger
    -0.16
    utable
    -0.15
    ôm
    -0.15
    ì²Ń
    -0.15
    space
    -0.15
     Haut
    -0.14
    onth
    -0.14
     NotImplemented
    -0.14
    axy
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
     hours
    0.28
     late
    0.28
     long
    0.28
    hours
    0.24
     marathon
    0.24
    long
    0.23
    Hours
    0.23
     Hours
    0.23
     shifts
    0.22
    -hours
    0.21
    Act Density 0.123%

    No Known Activations