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

    Neuronpedia

    INDEX
    Explanations

    directives prompting action or reminding about something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases encouraging action or reminders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheat
    -0.80
    Released
    -0.80
    ItemTracker
    -0.78
    é¾
    -0.74
    abase
    -0.67
     PsyNet
    -0.66
    aughtered
    -0.66
    inals
    -0.64
    isine
    -0.63
    Arab
    -0.63
    POSITIVE LOGITS
    fulness
    0.72
     remembered
    0.69
    theless
    0.68
    ful
    0.68
    fully
    0.67
     sweets
    0.65
     classics
    0.64
    pieces
    0.64
     remembering
    0.64
    fort
    0.62
    Act Density 0.012%

    No Known Activations