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

    Neuronpedia

    INDEX
    Explanations

    words related to predators or predatory behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to predators, particularly in discussions of behavior or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bel
    -0.77
    bles
    -0.74
    ilts
    -0.73
    stones
    -0.70
    gran
    -0.70
    monds
    -0.69
     provisional
    -0.69
    rique
    -0.68
    PE
    -0.67
    URN
    -0.67
    POSITIVE LOGITS
     predators
    1.36
     predator
    1.15
     prey
    1.12
     stalking
    0.90
     predatory
    0.85
    ervative
    0.84
     Predators
    0.81
    ervatives
    0.79
     Predator
    0.78
     behavi
    0.78
    Act Density 0.013%

    No Known Activations