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

    Neuronpedia

    INDEX
    Explanations

    references to the Sabbath

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sabbath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IZE
    -0.75
     Tigers
    -0.70
    stal
    -0.62
    most
    -0.62
     CONTROL
    -0.60
    lda
    -0.58
    piece
    -0.58
     mobilize
    -0.58
     appreciate
    -0.57
     isolate
    -0.57
    POSITIVE LOGITS
    abb
    1.52
    ucket
    1.02
    itt
    0.96
    azz
    0.95
    abis
    0.92
    arella
    0.91
    agn
    0.88
    arre
    0.86
    alist
    0.86
    oyle
    0.86
    Act Density 0.004%

    No Known Activations