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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making a change

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to action and instruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.60
    nai
    -0.57
    oult
    -0.56
     actionGroup
    -0.55
    anwhile
    -0.55
    achus
    -0.54
    selves
    -0.54
    aukee
    -0.52
    emetery
    -0.51
     Nanto
    -0.51
    POSITIVE LOGITS
     it
    1.88
     thereof
    1.17
     It
    1.11
    It
    1.07
    it
    1.06
    Its
    1.02
     them
    1.01
     its
    0.99
     therein
    0.98
     thereto
    0.97
    Act Density 1.667%

    No Known Activations