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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistics or numerical data

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the opening parenthesis symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flow
    -0.75
     retard
    -0.74
     intelligent
    -0.71
     reve
    -0.71
     millenn
    -0.71
     lull
    -0.71
     sincere
    -0.70
     occupancy
    -0.70
     sincerely
    -0.70
     cool
    -0.69
    POSITIVE LOGITS
    although
    1.75
    see
    1.70
    emphasis
    1.54
    which
    1.49
    though
    1.49
    unless
    1.47
    ?).
    1.46
    !).
    1.45
    Figure
    1.45
    among
    1.41
    Act Density 0.166%

    No Known Activations