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

    Neuronpedia

    INDEX
    Explanations

    phrases centered around the concept of "making" or "creating" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dou
    -0.15
    ikut
    -0.15
    _INITIALIZER
    -0.15
    tsky
    -0.14
    ÛĮÙĨÚ©
    -0.14
    tsy
    -0.14
    ãģ«ãģ¤
    -0.14
    aoke
    -0.14
    argin
    -0.14
    templ
    -0.14
    POSITIVE LOGITS
     sense
    0.24
     senses
    0.19
     Sense
    0.17
    sense
    0.17
     headlines
    0.16
     me
    0.15
     appearing
    0.15
     appearances
    0.14
    ButtonModule
    0.14
    ifference
    0.14
    Act Density 0.079%

    No Known Activations