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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and references related to documentation and administrative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    les
    -0.15
    zag
    -0.15
     Forge
    -0.15
     Luo
    -0.15
    130
    -0.14
    aus
    -0.14
    368
    -0.14
     Evet
    -0.13
    C
    -0.13
    164
    -0.13
    POSITIVE LOGITS
    GenerationStrategy
    0.17
    ixel
    0.17
    ñana
    0.17
    ãĤ¸ãĤ¢
    0.16
    spb
    0.15
    tics
    0.15
    iko
    0.14
    .visitMethod
    0.14
    sko
    0.14
    ixin
    0.14
    Act Density 0.033%

    No Known Activations