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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persistence or continued existence

    oai_token-act-pair · gpt-3.5-turbo

    themes related to persistence or continuity over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Secondly
    -0.74
    wcsstore
    -0.73
    ĪĴ
    -0.73
     elimination
    -0.68
     opposite
    -0.67
    Ĥİ
    -0.64
    usterity
    -0.62
    Ĵ
    -0.62
    pecially
    -0.62
    ttes
    -0.61
    POSITIVE LOGITS
     lingering
    0.93
     intact
    0.90
     unanswered
    0.87
     unsolved
    0.86
     unresolved
    0.84
     scars
    0.79
     stubborn
    0.77
     haun
    0.76
     residual
    0.75
     despite
    0.74
    Act Density 0.357%

    No Known Activations