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

    Neuronpedia

    INDEX
    Explanations

    dates presented in relation to significant events

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases and markers indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pecially
    -0.87
    emo
    -0.72
    estine
    -0.71
    serv
    -0.71
    urat
    -0.70
    arsh
    -0.69
    organic
    -0.67
    hots
    -0.66
    oras
    -0.66
    OW
    -0.65
    POSITIVE LOGITS
     still
    0.94
     reckoning
    0.80
     nearing
    0.76
     Congratulations
    0.73
     Mehran
    0.71
     anew
    0.70
    still
    0.68
     huh
    0.68
     hindsight
    0.66
     unresolved
    0.66
    Act Density 0.373%

    No Known Activations