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

    Neuronpedia

    INDEX
    Explanations

    frequency of the word "of" and its variations in relation to subjects and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raki
    -0.18
    rap
    -0.15
    ëŀĮ
    -0.15
    ibly
    -0.15
     evac
    -0.14
     Woj
    -0.14
     **************************************************************************
    -0.14
    icari
    -0.14
    riel
    -0.14
    ei
    -0.14
    POSITIVE LOGITS
    jom
    0.17
    /goto
    0.16
     Pink
    0.15
    persons
    0.15
    StateManager
    0.15
    /inet
    0.15
    heads
    0.15
    orrect
    0.15
     Reverse
    0.14
     neon
    0.14
    Act Density 0.001%

    No Known Activations