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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases related to specific phenomena and occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CI
    -0.65
    $.
    -0.64
     anyways
    -0.63
    wik
    -0.62
     ASAP
    -0.61
     anyway
    -0.60
     Saying
    -0.60
    ãĥ¥
    -0.57
     IPM
    -0.55
     Celt
    -0.55
    POSITIVE LOGITS
     emerged
    1.43
     emerges
    1.41
     ensued
    1.33
     awaits
    1.31
     arose
    1.25
     exists
    1.22
     accompanies
    1.21
     sprang
    1.20
     prevailed
    1.18
     existed
    1.14
    Act Density 1.792%

    No Known Activations