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

    Neuronpedia

    INDEX
    Explanations

    time-related concepts or events in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to periods or durations within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateg
    -0.77
    gru
    -0.67
    AIN
    -0.66
    urse
    -0.65
    chio
    -0.62
    oros
    -0.62
     Alps
    -0.60
    Case
    -0.60
     bluff
    -0.59
    itely
    -0.59
    POSITIVE LOGITS
    boarding
    0.75
     abroad
    0.74
    piece
    0.72
    rs
    0.71
    mates
    0.70
     flourishing
    0.70
     composing
    0.69
     tenure
    0.68
     mate
    0.68
    manship
    0.68
    Act Density 0.074%

    No Known Activations