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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws, regulations, and limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts that emphasize "of" relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LY
    -0.79
    Ô
    -0.75
    Enlarge
    -0.73
    BILITIES
    -0.73
    gob
    -0.71
    OV
    -0.71
     Kills
    -0.70
    2200
    -0.69
    eus
    -0.69
     istg
    -0.68
    POSITIVE LOGITS
     darkness
    0.76
     our
    0.72
     various
    0.71
     persuasion
    0.68
     those
    0.66
     civilization
    0.65
    piring
    0.64
     conscience
    0.64
     varying
    0.63
     everyday
    0.61
    Act Density 0.208%

    No Known Activations