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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political actions and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĿ
    -0.58
     ;)
    -0.56
     ðŁĻĤ
    -0.55
    -,
    -0.54
    ~
    -0.53
    —-
    -0.52
     TOD
    -0.52
     :)
    -0.52
     ounce
    -0.52
     afore
    -0.52
    POSITIVE LOGITS
    etheless
    1.07
     nonetheless
    0.74
     nevertheless
    0.73
     hereby
    0.66
     Pruitt
    0.62
    cigarettes
    0.62
    kefeller
    0.61
    ASHINGTON
    0.60
    iannopoulos
    0.59
    bably
    0.59
    Act Density 0.552%

    No Known Activations