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

    Neuronpedia

    INDEX
    Explanations

    verbs describing actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onet
    -0.67
    assetsadobe
    -0.66
     Metatron
    -0.62
     confir
    -0.62
    ickr
    -0.61
    /,
    -0.58
     misunder
    -0.58
    ,,,,
    -0.58
    areth
    -0.56
     Cosponsors
    -0.56
    POSITIVE LOGITS
    ynes
    0.64
    pak
    0.62
    chuk
    0.61
    icum
    0.57
     shine
    0.57
    ibel
    0.56
     occupants
    0.56
    DERR
    0.56
    otos
    0.55
    edo
    0.55
    Act Density 0.538%

    No Known Activations