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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to official designations or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.64
     ..."
    -0.62
    ire
    -0.61
    orum
    -0.61
    Bride
    -0.60
    î
    -0.60
    advertising
    -0.60
    pee
    -0.59
    Semitism
    -0.59
    Photo
    -0.59
    POSITIVE LOGITS
     moreover
    0.84
     however
    0.80
     therefore
    0.74
     furthermore
    0.68
    anwhile
    0.66
    ãĥį
    0.62
     ital
    0.59
     Cosponsors
    0.56
     contrast
    0.55
    yss
    0.54
    Act Density 1.326%

    No Known Activations