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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating group actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and related phrases that indicate ongoing action or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odor
    -0.69
    ascript
    -0.68
    ultan
    -0.62
    abus
    -0.61
    aiden
    -0.61
    negie
    -0.60
    quartered
    -0.60
     otherwise
    -0.60
     teasp
    -0.57
     Gener
    -0.56
    POSITIVE LOGITS
    here
    0.91
     gotta
    0.74
    adays
    0.73
    nir
    0.72
     finally
    0.71
     officially
    0.69
     wanna
    0.68
    aukee
    0.68
     lawy
    0.68
     realizes
    0.67
    Act Density 0.190%

    No Known Activations