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

    Neuronpedia

    INDEX
    Explanations

    phrases related to escape or running away

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fleeing" and related contexts of escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.77
    elist
    -0.75
    },{"
    -0.73
    Drive
    -0.71
    coe
    -0.67
     Ensure
    -0.65
    ifle
    -0.65
    tex
    -0.64
     purge
    -0.64
    lass
    -0.64
    POSITIVE LOGITS
     leaping
    1.88
     crashing
    1.87
     jumping
    1.83
     spinning
    1.78
     bouncing
    1.76
     behaving
    1.69
     ringing
    1.68
     speeding
    1.65
     fleeing
    1.64
     wandering
    1.63
    Act Density 0.070%

    No Known Activations