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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing additional information or context

    oai_token-act-pair · gpt-3.5-turbo

    elements of punctuation and structure in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tones
    -0.60
    warts
    -0.60
     downgrade
    -0.59
    iquette
    -0.59
    wcsstore
    -0.58
     unin
    -0.57
     charm
    -0.57
    ruciating
    -0.56
     CLSID
    -0.56
     pill
    -0.55
    POSITIVE LOGITS
    APTER
    0.76
    Exit
    0.75
    Continue
    0.75
    laughs
    0.73
     CONTIN
    0.71
    said
    0.70
    ]."
    0.69
    emphasis
    0.65
    ["
    0.64
    SPONSORED
    0.63
    Act Density 0.420%

    No Known Activations