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

    Neuronpedia

    INDEX
    Explanations

    phrases related to information, data, and opinions

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency phrases or common phrases that include the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.73
    umbledore
    -0.71
     someday
    -0.69
    esses
    -0.68
    ahime
    -0.67
    tch
    -0.67
    gal
    -0.67
    gur
    -0.67
    abwe
    -0.66
    omic
    -0.65
    POSITIVE LOGITS
     proceeds
    0.78
     except
    0.75
     depended
    0.72
     revolves
    0.71
     indications
    0.71
     sudden
    0.70
     mattered
    0.70
     aside
    0.70
     hinges
    0.69
     meshes
    0.69
    Act Density 0.133%

    No Known Activations