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

    Neuronpedia

    INDEX
    Explanations

    personal information or details about someone's actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.71
    sylv
    -0.52
    ety
    -0.51
    asca
    -0.51
    herent
    -0.50
    ocl
    -0.48
    UF
    -0.48
     Cth
    -0.48
    aha
    -0.46
    igen
    -0.46
    POSITIVE LOGITS
     huh
    0.84
     however
    0.83
     albeit
    0.81
     which
    0.77
     though
    0.77
     although
    0.77
     but
    0.76
     namely
    0.75
     including
    0.71
     preferably
    0.71
    Act Density 0.556%

    No Known Activations