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

    Neuronpedia

    INDEX
    Explanations

    terms related to the use of a specific brand or type of equipment, possibly a weapon

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Taser" and its variations in the context of law enforcement use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.79
    endor
    -0.78
    orio
    -0.75
    catentry
    -0.74
    reprene
    -0.70
    orno
    -0.69
    ammed
    -0.69
    ersen
    -0.68
    ourn
    -0.66
    ophers
    -0.66
    POSITIVE LOGITS
    bang
    0.76
    ministic
    0.70
    idon
    0.70
    gency
    0.68
    xes
    0.66
    bomb
    0.66
    inus
    0.66
    pling
    0.65
    cheon
    0.64
    ARP
    0.63
    Act Density 0.027%

    No Known Activations