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

    Neuronpedia

    INDEX
    Explanations

    terms related to news outlets

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and words related to news and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.68
    ï¸ı
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    zona
    -0.62
    DEBUG
    -0.57
    LINE
    -0.56
     anecd
    -0.55
     constituent
    -0.55
    DoS
    -0.54
    ashtra
    -0.54
    POSITIVE LOGITS
    angled
    0.90
    eers
    0.80
    phrine
    0.78
    leans
    0.76
    izons
    0.74
     Cinema
    0.72
    aldo
    0.68
    enhagen
    0.67
    ounds
    0.67
    ieties
    0.65
    Act Density 0.098%

    No Known Activations