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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to technology and professional fields

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or titles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sep
    -0.72
    ciplinary
    -0.69
    Picture
    -0.66
    "))
    -0.64
    Interest
    -0.64
    Aug
    -0.61
    enes
    -0.61
    Dist
    -0.60
    apse
    -0.60
    olulu
    -0.60
    POSITIVE LOGITS
    !).
    0.95
    ?).
    0.88
    )</
    0.84
     ).
    0.79
    ãĥ³ãĤ¸
    0.79
    -)
    0.75
    ).
    0.75
    ãĢij
    0.72
    }.
    0.70
    !),
    0.70
    Act Density 0.857%

    No Known Activations