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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or terms related to Tol

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and the theme of vilification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depreciation
    -0.66
    ILY
    -0.64
     showers
    -0.64
     shower
    -0.63
    boards
    -0.63
    board
    -0.62
    manship
    -0.62
     stump
    -0.62
    eering
    -0.61
    eding
    -0.61
    POSITIVE LOGITS
     Nadu
    0.82
    sie
    0.82
    edo
    0.82
    ove
    0.81
    achev
    0.80
    entially
    0.79
    ibr
    0.78
    irtual
    0.77
    ieve
    0.73
    ima
    0.73
    Act Density 0.027%

    No Known Activations