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

    Neuronpedia

    INDEX
    Explanations

    instances of "de facto" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eteria
    -0.17
    ona
    -0.17
     Herz
    -0.16
    aza
    -0.15
    aryl
    -0.14
    illo
    -0.14
    "value
    -0.14
    emann
    -0.14
    emic
    -0.14
     prop
    -0.13
    POSITIVE LOGITS
    STONE
    0.15
    relations
    0.15
     intercept
    0.15
    å²
    0.15
    rieve
    0.14
    iew
    0.14
    razier
    0.14
    ews
    0.14
    óc
    0.13
    亮
    0.13
    Act Density 0.004%

    No Known Activations