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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and criminal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verages
    -0.78
    uploads
    -0.68
    mostly
    -0.66
    ateurs
    -0.61
    faced
    -0.60
    DragonMagazine
    -0.59
    sbm
    -0.59
     Presidents
    -0.55
    é¾įå¥ij士
    -0.53
    ©¶æ¥µ
    -0.53
    POSITIVE LOGITS
     something
    1.42
     someone
    1.39
     somebody
    1.34
    someone
    1.30
     another
    1.24
    something
    1.16
    Someone
    1.10
    another
    1.05
    Something
    1.03
     Someone
    1.03
    Act Density 0.655%

    No Known Activations