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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ·»
    -0.15
    ancellor
    -0.15
    lej
    -0.15
    raya
    -0.15
    jadi
    -0.15
     KeyValue
    -0.14
    ey
    -0.14
    atalog
    -0.14
    же
    -0.14
     bì
    -0.14
    POSITIVE LOGITS
    ி
    0.15
     spons
    0.15
    robat
    0.15
    Ïĥκε
    0.15
    ars
    0.15
    erra
    0.15
    acer
    0.15
    162
    0.15
    ardon
    0.14
    lava
    0.14
    Act Density 0.047%

    No Known Activations