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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action and control

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.72
     RAD
    -0.71
     Gleaming
    -0.68
     Sandwich
    -0.65
     cyan
    -0.63
     assemb
    -0.62
     colonial
    -0.61
     shack
    -0.61
    代
    -0.61
     guiActiveUn
    -0.60
    POSITIVE LOGITS
    £
    0.98
    Ĵ
    0.93
    ı
    0.89
    Ķ
    0.87
    lege
    0.85
    ĵ
    0.84
    uve
    0.82
    ij
    0.80
    been
    0.79
    «
    0.79
    Act Density 0.046%

    No Known Activations