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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating measurement or comparison, often related to cultural or societal changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osterone
    -0.62
     Ort
    -0.61
    dain
    -0.57
    ivities
    -0.57
     marg
    -0.57
     Valid
    -0.56
     filibuster
    -0.56
    arat
    -0.56
    employment
    -0.55
     Maxim
    -0.55
    POSITIVE LOGITS
     fruition
    0.85
     nearer
    0.72
     blows
    0.72
     handy
    0.71
    soon
    0.71
     reinforcements
    0.70
     closer
    0.68
    enium
    0.67
    itely
    0.66
    ither
    0.65
    Act Density 0.104%

    No Known Activations