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

    Neuronpedia

    INDEX
    Explanations

    the initial "S" characters, likely indicating citations or references in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uns
    -0.19
    urre
    -0.19
    unn
    -0.19
    emi
    -0.19
    illy
    -0.18
    acro
    -0.18
    usan
    -0.18
    uff
    -0.17
    ally
    -0.17
    ister
    -0.17
    POSITIVE LOGITS
    olt
    0.18
    zn
    0.17
    viders
    0.17
    og
    0.17
    zu
    0.16
    rin
    0.16
    odian
    0.16
    uter
    0.16
    lez
    0.15
    iv
    0.15
    Act Density 0.035%

    No Known Activations