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

    Neuronpedia

    INDEX
    Explanations

    connections or relationships between different factors or variables

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing statistical relationships and correlations between different variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.85
    scrib
    -0.73
     Saud
    -0.72
     Vaugh
    -0.71
    ircraft
    -0.71
    fal
    -0.69
    Tok
    -0.68
    ofi
    -0.67
    Aud
    -0.66
    aniel
    -0.64
    POSITIVE LOGITS
     negatively
    0.97
     outcomes
    0.95
     susceptibility
    0.91
     influencing
    0.87
     determining
    0.86
     factors
    0.84
     causation
    0.83
     measurable
    0.83
     shaping
    0.83
     variability
    0.80
    Act Density 0.208%

    No Known Activations