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

    Neuronpedia

    INDEX
    Explanations

    words related to predatory behavior or potential dangers

    oai_token-act-pair · gpt-3.5-turbo

    references to predators and predatory behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     provisional
    -0.79
    oard
    -0.75
    bel
    -0.75
    gran
    -0.74
    VK
    -0.72
    rique
    -0.70
    ahon
    -0.69
    UGE
    -0.68
    rief
    -0.68
    printed
    -0.68
    POSITIVE LOGITS
     predators
    1.29
     prey
    1.13
     predator
    1.07
     Predators
    0.85
    ervative
    0.84
     stalking
    0.84
     predatory
    0.80
     instincts
    0.79
    ervatives
    0.78
     carniv
    0.78
    Act Density 0.018%

    No Known Activations