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

    Neuronpedia

    INDEX
    Explanations

    questioning or expressing concern about something in a critical manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases that question the consideration of others' needs or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arm
    -0.74
    Ãį
    -0.72
    Published
    -0.71
    River
    -0.70
    ¯¯¯¯¯¯¯¯
    -0.70
    ells
    -0.69
    Sher
    -0.68
    oppy
    -0.68
    Thompson
    -0.68
    imb
    -0.68
    POSITIVE LOGITS
    ...?
    0.90
    !?
    0.79
     those
    0.75
     protecting
    0.71
    ?!
    0.70
     fairness
    0.69
    !?"
    0.68
     grandchildren
    0.68
    ?
    0.67
    ?:
    0.66
    Act Density 0.031%

    No Known Activations