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

    Neuronpedia

    INDEX
    Explanations

    current events or status updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the current state or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.79
    riz
    -0.76
    achine
    -0.76
     kindred
    -0.75
    abilia
    -0.71
    Chip
    -0.70
    essen
    -0.70
     vengeance
    -0.69
    uddin
    -0.68
    esses
    -0.65
    POSITIVE LOGITS
     ratified
    0.80
    adays
    0.79
    nown
    0.72
     consisted
    0.72
     extant
    0.72
     prevailing
    0.68
     pegged
    0.66
     rated
    0.64
     exists
    0.64
    Supported
    0.63
    Act Density 0.064%

    No Known Activations