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

    Neuronpedia

    INDEX
    Explanations

    words related to screen, print, and restore

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restorative concepts and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bab
    -0.62
    Reply
    -0.62
     Ascension
    -0.61
     Way
    -0.60
    ism
    -0.58
     flock
    -0.58
     Sins
    -0.57
     Setup
    -0.57
     Hedge
    -0.56
    rosis
    -0.56
    POSITIVE LOGITS
    orative
    4.24
    itious
    1.15
    icative
    1.08
     decriminal
    1.04
    creen
    1.04
    utic
    0.96
    itous
    0.94
    utical
    0.93
    unky
    0.90
    ulative
    0.90
    Act Density 0.042%

    No Known Activations