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

    Neuronpedia

    INDEX
    Explanations

    quotes from speakers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previously
    -0.16
    åĨĬ
    -0.15
    ableObject
    -0.15
    oco
    -0.14
     Lar
    -0.14
     write
    -0.14
    panion
    -0.14
    amburger
    -0.14
     Demir
    -0.14
    amat
    -0.14
    POSITIVE LOGITS
     informs
    0.17
    inform
    0.17
    illance
    0.17
     hoped
    0.16
    èį
    0.16
     regret
    0.16
    abox
    0.16
     further
    0.15
    ingers
    0.15
     inform
    0.14
    Act Density 0.054%

    No Known Activations