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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking a stand or standing up for something

    oai_token-act-pair · gpt-3.5-turbo

    references to self-defense laws and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.67
    vous
    -0.66
    ashington
    -0.63
    elf
    -0.63
    è¦ļéĨĴ
    -0.62
    NT
    -0.62
    ghan
    -0.61
    haus
    -0.60
    maps
    -0.60
     Verb
    -0.58
    POSITIVE LOGITS
     doors
    0.75
     pedest
    0.75
    ailability
    0.74
     desks
    0.71
     shoulders
    0.71
    anded
    0.70
    atoon
    0.70
    ailable
    0.69
    iage
    0.67
    oppable
    0.64
    Act Density 0.075%

    No Known Activations