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

    Neuronpedia

    INDEX
    Explanations

    references to risk and risk-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tring
    -0.17
    pany
    -0.15
    zend
    -0.15
    PIP
    -0.15
    PTION
    -0.15
    rina
    -0.14
    hind
    -0.14
    нимаеÑĤ
    -0.14
    meer
    -0.14
    uration
    -0.14
    POSITIVE LOGITS
    iest
    0.33
    ier
    0.30
    iness
    0.25
     factors
    0.25
     appetite
    0.22
     av
    0.22
     Factors
    0.22
    ily
    0.21
     factor
    0.20
     exposure
    0.20
    Act Density 0.032%

    No Known Activations