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

    Neuronpedia

    INDEX
    Explanations

    transitions indicating a conclusion or result

    oai_token-act-pair · gpt-3.5-turbo

    statements signaling conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},"
    -0.62
     ______
    -0.59
    ga
    -0.58
    duction
    -0.57
     Rumble
    -0.56
     upgr
    -0.56
    GER
    -0.55
     Barb
    -0.55
     exclusively
    -0.55
     burg
    -0.55
    POSITIVE LOGITS
    fter
    0.83
    forth
    0.82
    pite
    0.77
    ername
    0.76
    forward
    0.76
    aucuses
    0.74
    ccording
    0.73
    entimes
    0.72
    hester
    0.72
    noon
    0.70
    Act Density 0.034%

    No Known Activations