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

    Neuronpedia

    INDEX
    Explanations

    words related to budgeting and allocations

    oai_token-act-pair · gpt-3.5-turbo

    indicators of the end of text or paragraph breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifying
    -0.78
    ified
    -0.75
    KING
    -0.75
    ileaks
    -0.75
    ling
    -0.74
     Pupp
    -0.71
    ifier
    -0.71
    MJ
    -0.70
    cer
    -0.69
    idian
    -0.69
    POSITIVE LOGITS
     Osw
    0.79
    artment
    0.78
    ircraft
    0.76
    pex
    0.73
    xual
    0.70
    ãĥĥãĥĪ
    0.69
     ratios
    0.68
    avorite
    0.67
    ĺħ
    0.66
    Ĥª
    0.66
    Act Density 0.084%

    No Known Activations