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

    Neuronpedia

    INDEX
    Explanations

    future predictions or speculations

    oai_token-act-pair · gpt-3.5-turbo

    predictions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eret
    -0.89
     yesterday
    -0.75
     lately
    -0.69
    mist
    -0.68
     recent
    -0.67
     earlier
    -0.64
     beforehand
    -0.64
     persisted
    -0.63
     Darling
    -0.63
     persists
    -0.62
    POSITIVE LOGITS
     surpass
    0.82
     realize
    0.75
    ypes
    0.73
     definitively
    0.69
     finally
    0.68
    ãĥ¯ãĥ³
    0.68
     realise
    0.68
    é¾į
    0.67
    alia
    0.67
    ãĥķãĤ¡
    0.66
    Act Density 0.507%

    No Known Activations