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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases, specifying time

    oai_token-act-pair · gpt-3.5-turbo

    temporal expressions indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amate
    -0.71
    cientious
    -0.69
    inite
    -0.69
    exec
    -0.66
    found
    -0.64
    itational
    -0.64
    uns
    -0.63
    database
    -0.63
    iom
    -0.63
    iterranean
    -0.63
    POSITIVE LOGITS
     ago
    0.91
     Ago
    0.78
    aneously
    0.77
     eve
    0.76
     shy
    0.73
     ahead
    0.71
     elapsed
    0.70
     pregnant
    0.69
    etter
    0.66
     Weeks
    0.63
    Act Density 0.101%

    No Known Activations