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

    Neuronpedia

    INDEX
    Explanations

    key actions and indicators related to detection and prevention in medical and safety contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plash
    -0.15
    essen
    -0.15
    tesy
    -0.14
     experiences
    -0.14
    ARSE
    -0.13
    ิร
    -0.13
    ALLOC
    -0.13
    izzato
    -0.13
    _INITIALIZER
    -0.13
    rov
    -0.13
    POSITIVE LOGITS
     potential
    0.33
     signs
    0.31
     suspicious
    0.27
     presence
    0.27
     Potential
    0.27
    potential
    0.26
     Signs
    0.26
     impending
    0.25
     possible
    0.24
     Presence
    0.24
    Act Density 0.177%

    No Known Activations