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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing degrees of likelihood or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.89
    restling
    -0.75
    mental
    -0.75
    milo
    -0.72
    ests
    -0.71
    utic
    -0.69
    hyde
    -0.69
    issance
    -0.68
    clerosis
    -0.68
    berra
    -0.68
    POSITIVE LOGITS
     quaint
    0.80
     innocuous
    0.79
     contradiction
    0.68
     Zeal
    0.68
     bookmark
    0.67
     cliché
    0.67
     ut
    0.67
     deviation
    0.65
     fitting
    0.64
     naive
    0.64
    Act Density 0.168%

    No Known Activations