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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a need for external validation or support

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the necessity of citations or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.96
    edIn
    -0.77
    Monitor
    -0.76
    apesh
    -0.75
    Grid
    -0.74
    Pur
    -0.73
    Console
    -0.72
    FTWARE
    -0.71
    ahime
    -0.71
    Bench
    -0.71
    POSITIVE LOGITS
     redacted
    0.88
    çīĪ
    0.71
     sentence
    0.70
     omitted
    0.70
     reserved
    0.68
     included
    0.65
     translator
    0.65
    ities
    0.65
     spoilers
    0.65
     ital
    0.64
    Act Density 0.106%

    No Known Activations