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

    Neuronpedia

    INDEX
    Explanations

    terms related to similarities and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lod
    -0.17
    renom
    -0.16
    lish
    -0.15
    eter
    -0.15
    ndon
    -0.15
    ete
    -0.14
    stell
    -0.14
    ppo
    -0.14
    agar
    -0.14
    tt
    -0.14
    POSITIVE LOGITS
    ép
    0.15
    inde
    0.15
    earer
    0.15
    .setOutput
    0.15
     quot
    0.15
     bi
    0.14
    499
    0.14
    deaux
    0.14
     humanity
    0.14
    éĥ¡
    0.14
    Act Density 0.093%

    No Known Activations