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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those related to times and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cart
    -0.66
     fencing
    -0.64
     scenery
    -0.63
     pastoral
    -0.63
     precip
    -0.62
     bleeding
    -0.62
     creeping
    -0.61
     separat
    -0.61
     vel
    -0.61
     plateau
    -0.60
    POSITIVE LOGITS
    120
    0.90
    148
    0.88
    118
    0.84
    145
    0.83
    114
    0.83
    âĢ²
    0.83
     sqor
    0.82
    203
    0.82
    147
    0.82
    802
    0.82
    Act Density 0.156%

    No Known Activations