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

    Neuronpedia

    INDEX
    Explanations

    requests for additional information or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rike
    -0.15
    SSERT
    -0.15
    ashtra
    -0.15
     enlightened
    -0.15
    jang
    -0.14
    ÅĻi
    -0.14
    terra
    -0.14
     hers
    -0.14
    ulg
    -0.13
    umlu
    -0.13
    POSITIVE LOGITS
    anlar
    0.16
    éł
    0.15
    SKTOP
    0.15
    /rfc
    0.14
    aran
    0.14
    an
    0.14
     ÐĶив
    0.13
    Cascade
    0.13
    andra
    0.13
    276
    0.13
    Act Density 0.010%

    No Known Activations