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

    Neuronpedia

    INDEX
    Explanations

    references to the process of generating documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hooks
    -0.16
    amak
    -0.16
    RYPTO
    -0.16
    mbH
    -0.15
    ateur
    -0.14
     Champ
    -0.14
    etik
    -0.14
    gesi
    -0.14
    SetName
    -0.14
    DRV
    -0.14
    POSITIVE LOGITS
    heimer
    0.16
    lish
    0.15
     Mits
    0.15
    hang
    0.15
     bone
    0.15
     deal
    0.14
     atomic
    0.14
    .getInputStream
    0.14
    indy
    0.14
     пÑĢик
    0.14
    Act Density 0.016%

    No Known Activations