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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing or initiating actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inst" and its variations, relating to instilling or installing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.85
    livious
    -0.72
     Nanto
    -0.71
     KING
    -0.67
     Skydragon
    -0.66
    ļéĨĴ
    -0.66
     Clyde
    -0.65
    jri
    -0.65
    Downloadha
    -0.65
    FACE
    -0.65
    POSITIVE LOGITS
    igator
    1.09
    igators
    1.06
    igated
    0.99
    agram
    0.95
    ru
    0.93
    igating
    0.91
    igation
    0.90
    uates
    0.90
    rave
    0.87
    ument
    0.87
    Act Density 0.011%

    No Known Activations