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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal cases and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.61
    gypt
    -0.61
    ukong
    -0.59
     PLEASE
    -0.58
    ourning
    -0.56
     âĵĺ
    -0.55
    igion
    -0.53
    resy
    -0.52
    iens
    -0.52
    ':
    -0.52
    POSITIVE LOGITS
    ).[
    0.71
    ).
    0.58
     phr
    0.54
     unsuccessfully
    0.54
    !).
    0.53
     beforehand
    0.51
     pree
    0.49
     gram
    0.49
    ?).
    0.49
    atro
    0.49
    Act Density 2.699%

    No Known Activations