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

    Neuronpedia

    INDEX
    Explanations

    references to avant-garde themes or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.15
    ovol
    -0.15
    iske
    -0.15
    alg
    -0.15
    leur
    -0.14
    ModelProperty
    -0.14
    ãĥ³ãĤ¯
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    isans
    -0.14
    eÄį
    -0.14
    POSITIVE LOGITS
     Av
    0.21
    ance
    0.18
    Av
    0.17
    anche
    0.17
    iling
    0.17
    551
    0.17
    anches
    0.17
    .Av
    0.17
    139
    0.16
    140
    0.16
    Act Density 0.023%

    No Known Activations