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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contributions, characteristics of works, and references to significant achievements or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    615
    -0.18
    orc
    -0.15
    oucher
    -0.15
     Laurie
    -0.14
    ilen
    -0.14
    ØŃص
    -0.14
    otte
    -0.14
     Sat
    -0.14
    ers
    -0.14
    ázd
    -0.14
    POSITIVE LOGITS
    odzi
    0.17
    ija
    0.17
    way
    0.15
    øj
    0.15
    uraa
    0.15
    icient
    0.15
    ARRANT
    0.15
    ãĤ¸ãĥ¥
    0.15
     tiener
    0.15
    ijken
    0.15
    Act Density 0.287%

    No Known Activations