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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oked
    -0.75
    olitan
    -0.72
    ailable
    -0.71
    accompanied
    -0.67
    icum
    -0.66
    rongh
    -0.65
    etheless
    -0.65
    conservancy
    -0.64
    ribune
    -0.63
    cientious
    -0.62
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.76
     Entered
    0.69
     ±
    0.67
     Wraith
    0.60
    ))))
    0.60
     Qi
    0.59
    Ùħ
    0.59
     Rowling
    0.58
    Jr
    0.58
     onwards
    0.58
    Act Density 0.134%

    No Known Activations