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

    Neuronpedia

    INDEX
    Explanations

    physical actions or events that have some kind of impact on people

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Secondly
    -0.72
    =>
    -0.69
    apest
    -0.67
     =>
    -0.67
    yet
    -0.66
     Secondly
    -0.65
    alg
    -0.62
    ','
    -0.60
    now
    -0.58
     ])
    -0.57
    POSITIVE LOGITS
     during
    1.34
     after
    1.27
     when
    1.25
    during
    1.17
     while
    1.10
     following
    1.09
     afterward
    1.04
    when
    1.04
     shortly
    0.97
     amid
    0.95
    Act Density 0.860%

    No Known Activations