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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with "Well,"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that conveys a pause or transition in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footprint
    -0.68
    İĭ
    -0.67
    è¦ļéĨĴ
    -0.63
    atile
    -0.62
    emo
    -0.60
    shown
    -0.59
     vortex
    -0.59
     lightsaber
    -0.58
     cutter
    -0.58
     appliance
    -0.58
    POSITIVE LOGITS
     yeah
    1.02
    yeah
    0.92
     uh
    0.89
     yes
    0.85
     guess
    0.81
     hello
    0.79
     fortunately
    0.76
     sorry
    0.76
     thank
    0.75
     luckily
    0.75
    Act Density 0.046%

    No Known Activations