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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement accountability

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include a specific punctuation mark or a series of repetitive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zos
    -0.71
    lass
    -0.68
    cha
    -0.63
    sw
    -0.60
    RM
    -0.59
    abase
    -0.59
    JV
    -0.57
    qv
    -0.57
    jon
    -0.56
     ;;
    -0.55
    POSITIVE LOGITS
     respectively
    1.18
     depending
    0.85
    depending
    0.81
     whichever
    0.69
     alike
    0.66
     carbohyd
    0.63
     aspects
    0.63
     approaches
    0.61
    åĤ
    0.60
    uca
    0.58
    Act Density 0.184%

    No Known Activations