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

    Neuronpedia

    INDEX
    Explanations

    numerical symbols and measurements

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inator
    -0.80
    ¿½
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.72
     omn
    -0.65
    Ĥ¬
    -0.63
    unia
    -0.63
     oun
    -0.61
    ĻĤ
    -0.61
     eleph
    -0.60
     plur
    -0.59
    POSITIVE LOGITS
    tm
    0.72
     (*
    0.69
    Deal
    0.69
    ouls
    0.68
    dn
    0.68
     olds
    0.67
    FIELD
    0.67
    ugg
    0.67
    drivers
    0.66
    mop
    0.66
    Act Density 0.045%

    No Known Activations