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

    Neuronpedia

    INDEX
    Explanations

    terms related to research methodology and evidence-based conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.79
    TagMode
    -0.78
    WriteBarrier
    -0.76
    InjectAttribute
    -0.76
    InvalidProtocol
    -0.65
     noqa
    -0.65
    SourceChecksum
    -0.65
     defaultstate
    -0.64
    RenderAtEndOf
    -0.61
     manières
    -0.61
    POSITIVE LOGITS
     observations
    1.35
     observation
    1.16
    observations
    1.13
     interviews
    1.05
     recent
    1.04
     anecdotal
    0.97
    observation
    0.96
     experience
    0.93
     observed
    0.93
     observa
    0.88
    Act Density 1.055%

    No Known Activations