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

    Neuronpedia

    INDEX
    Explanations

    words related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    words related to conditions and outcomes in legal and regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foreign
    -0.55
     Templ
    -0.52
    angel
    -0.52
    illary
    -0.52
    entimes
    -0.52
    é¾įå¥ij士
    -0.52
    atever
    -0.51
    ourt
    -0.50
    itol
    -0.50
    è¦ļéĨĴ
    -0.49
    POSITIVE LOGITS
     varied
    0.52
     crochet
    0.52
     smoothly
    0.48
    :[
    0.48
    verty
    0.47
     Netanyahu
    0.46
     Burns
    0.46
     muted
    0.46
     itself
    0.46
     snail
    0.46
    Act Density 0.784%

    No Known Activations