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

    Neuronpedia

    INDEX
    Explanations

    occurrences of property damage and destruction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of damage or destruction to property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.74
     congratulations
    -0.74
     Ago
    -0.74
    isSpecialOrderable
    -0.71
     comparisons
    -0.71
     congratulate
    -0.69
     formulas
    -0.68
     Reasons
    -0.67
     impulses
    -0.65
    Guide
    -0.65
    POSITIVE LOGITS
     destroyed
    1.14
     breached
    1.14
     confiscated
    1.13
     vandal
    1.09
     emptied
    1.08
     shut
    1.06
     revoked
    1.06
     damaged
    1.05
     torn
    1.04
     severed
    1.04
    Act Density 0.242%

    No Known Activations