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

    Neuronpedia

    INDEX
    Explanations

    examples of imaginative or fictional elements in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.33
     ---
    -0.29
     âĢIJ
    -0.27
     -↵
    -0.27
     ---↵
    -0.26
     -↵↵
    -0.25
     —
    -0.25
     ãĢľ
    -0.25
     âĪĴ
    -0.24
     —↵
    -0.24
    POSITIVE LOGITS
    –
    0.64
    –↵↵
    0.48
    –and
    0.45
    Âĸ
    0.38
    .–
    0.35
    ->
    0.31
    --
    0.29
    --[
    0.25
    ÙĢ
    0.24
    ÙĢÙĦ
    0.23
    Act Density 0.059%

    No Known Activations