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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "share" and related options or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tr
    -0.16
     sign
    -0.16
    mund
    -0.15
     Mine
    -0.15
    fur
    -0.15
    uta
    -0.15
    f
    -0.15
    anut
    -0.15
    رج
    -0.14
     Liebe
    -0.14
    POSITIVE LOGITS
    arget
    0.20
    าะ
    0.17
    umi
    0.15
    .updateDynamic
    0.15
    untu
    0.15
    errer
    0.15
    ernel
    0.15
    HLT
    0.14
     escorte
    0.14
    _ASSUME
    0.14
    Act Density 0.003%

    No Known Activations