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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various actions or intentions such as expressing desire, possibility, or expectation

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating potential or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Previously
    -0.67
    su
    -0.65
     Turns
    -0.62
    trap
    -0.62
    Dam
    -0.60
    Wars
    -0.60
    Recently
    -0.59
    Details
    -0.59
    linger
    -0.59
    Below
    -0.58
    POSITIVE LOGITS
    whatever
    0.73
     âĢ¦"
    0.66
     nurses
    0.63
     clot
    0.63
    ','
    0.62
    00200000
    0.61
     regulators
    0.60
    igi
    0.60
     humili
    0.60
     tsun
    0.60
    Act Density 0.329%

    No Known Activations