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

    Neuronpedia

    INDEX
    Explanations

    questions and statements related to inquiry or investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     credit
    -0.16
     Credit
    -0.15
    Credit
    -0.14
    ãĥ¼ãĥī
    -0.14
    मर
    -0.14
    ÚĺÙĨ
    -0.14
    poons
    -0.14
    igor
    -0.14
     spo
    -0.14
    gree
    -0.14
    POSITIVE LOGITS
     Rankings
    0.16
    bash
    0.15
     cock
    0.15
    adele
    0.15
    aepernick
    0.15
    redo
    0.15
    afs
    0.14
     Ukra
    0.14
    _NC
    0.14
    ůj
    0.14
    Act Density 0.059%

    No Known Activations