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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing context or reasoning

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YING
    -0.73
    eware
    -0.72
    unless
    -0.71
    ievers
    -0.68
    iband
    -0.68
    fits
    -0.68
    arter
    -0.66
    _-
    -0.66
    Bind
    -0.65
    thinking
    -0.65
    POSITIVE LOGITS
     circumstances
    1.27
     nature
    1.17
     recent
    1.16
     seriousness
    1.11
     popularity
    1.11
     propensity
    1.10
     proximity
    1.07
     severity
    1.05
     history
    1.04
     prevalence
    1.04
    Act Density 0.153%

    No Known Activations