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

    Neuronpedia

    INDEX
    Explanations

    references to output files and their associated paths in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :///
    -0.14
    олеÑĤ
    -0.14
     cul
    -0.14
     Talent
    -0.14
    icia
    -0.14
     bo
    -0.14
    toi
    -0.14
    agini
    -0.14
    kus
    -0.14
    undra
    -0.13
    POSITIVE LOGITS
    =output
    0.21
     output
    0.20
    .setOutput
    0.19
     OUTPUT
    0.18
     Output
    0.18
    output
    0.17
    acho
    0.16
    (output
    0.16
    .Output
    0.16
    (Output
    0.16
    Act Density 0.084%

    No Known Activations