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

    Neuronpedia

    INDEX
    Explanations

    actions related to clearing or freeing something

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with removal, clearing, or resolution of issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.71
    lihood
    -0.70
    ista
    -0.67
     headlined
    -0.67
     option
    -0.64
     surrounded
    -0.63
    itta
    -0.63
    oret
    -0.63
     reserved
    -0.61
    andum
    -0.60
    POSITIVE LOGITS
    ulate
    0.95
    imize
    0.91
    lift
    0.87
    cise
    0.78
    uate
    0.77
    strate
    0.75
    iate
    0.74
    due
    0.73
    balance
    0.71
    itate
    0.71
    Act Density 0.109%

    No Known Activations