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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸įåĪ°
    -0.16
    isch
    -0.16
    .Îł
    -0.15
    çĵ¶
    -0.14
    andan
    -0.14
    ãĤ¡
    -0.14
    870
    -0.14
    ÐĴС
    -0.14
    strup
    -0.14
    spoken
    -0.13
    POSITIVE LOGITS
    osc
    0.16
    nis
    0.15
     carr
    0.14
    лим
    0.14
    ilde
    0.14
    plode
    0.14
    ITU
    0.14
    erah
    0.14
    ase
    0.13
    etr
    0.13
    Act Density 0.146%

    No Known Activations