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

    Neuronpedia

    INDEX
    Explanations

    common words or phrases used repetitively across different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "many."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.84
    atum
    -0.76
    adiator
    -0.74
    opia
    -0.72
    ade
    -0.72
    abad
    -0.70
    ocracy
    -0.69
    ħĭ
    -0.68
    isition
    -0.68
    ADVERTISEMENT
    -0.67
    POSITIVE LOGITS
    body
    1.05
     times
    0.90
     commenters
    0.82
    theless
    0.82
     observers
    0.81
     aspects
    0.81
     similarities
    0.81
     unanswered
    0.80
     facets
    0.80
     commentators
    0.80
    Act Density 0.065%

    No Known Activations