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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation or conjecture

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of inability or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     methodological
    -0.61
     periodically
    -0.61
     mull
    -0.59
     defe
    -0.55
     contrace
    -0.55
     enrol
    -0.54
     review
    -0.53
     dele
    -0.53
     revert
    -0.53
     administ
    -0.52
    POSITIVE LOGITS
    bleacher
    0.66
    til
    0.66
     dreamed
    0.65
    ussed
    0.63
     nor
    0.62
    cedented
    0.62
    REAM
    0.59
    quite
    0.59
    azed
    0.59
    Sab
    0.58
    Act Density 0.289%

    No Known Activations