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

    Neuronpedia

    INDEX
    Explanations

    descriptive quantities and characteristics related to objects and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.70
    akings
    -0.66
    PDATE
    -0.66
    icter
    -0.66
    Reviewer
    -0.65
    acea
    -0.65
     notwithstanding
    -0.64
    undown
    -0.63
    OUP
    -0.63
     replacements
    -0.62
    POSITIVE LOGITS
     pedest
    1.00
     bushes
    0.90
    stretched
    0.89
     unsuspecting
    0.86
     oak
    0.86
     rooft
    0.85
     windshield
    0.85
     holes
    0.84
     mound
    0.83
     skysc
    0.83
    Act Density 0.332%

    No Known Activations