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

    Neuronpedia

    INDEX
    Explanations

    words related to predatory behavior and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to predators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    monds
    -0.80
    bel
    -0.74
    ahon
    -0.71
    bles
    -0.70
     provisional
    -0.70
    rique
    -0.69
    urn
    -0.69
    oard
    -0.69
    stones
    -0.68
     Luck
    -0.66
    POSITIVE LOGITS
     predators
    1.10
     prey
    1.02
     predator
    0.92
     instinct
    0.89
     instincts
    0.88
     stalking
    0.84
     predatory
    0.84
     lurking
    0.81
     Predators
    0.80
     prow
    0.79
    Act Density 0.021%

    No Known Activations