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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases containing special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     detail
    -0.60
     dot
    -0.54
     lift
    -0.54
    ction
    -0.53
     blot
    -0.53
    .�
    -0.53
     downed
    -0.52
     fend
    -0.51
     Recre
    -0.51
     Gym
    -0.51
    POSITIVE LOGITS
    there
    1.04
    then
    0.96
    they
    0.89
    should
    0.78
    we
    0.78
    ternity
    0.78
    these
    0.78
    DCS
    0.77
    this
    0.77
    older
    0.76
    Act Density 0.143%

    No Known Activations