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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that suggest political or social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysi
    -0.07
    verts
    -0.07
    æ³
    -0.07
    ä¿
    -0.07
    ipher
    -0.07
    verting
    -0.07
    ownt
    -0.06
    vert
    -0.06
    //{{
    -0.06
    ltk
    -0.06
    POSITIVE LOGITS
    abouts
    0.07
    oretical
    0.07
    iginal
    0.07
    ings
    0.06
    oval
    0.06
    stub
    0.06
    awning
    0.06
    ingly
    0.06
    INGS
    0.06
     nuts
    0.06
    Act Density 0.117%

    No Known Activations