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

    Neuronpedia

    INDEX
    Explanations

    expressions of high quality and positive evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hip
    -0.16
    -0.15
    omit
    -0.14
    nette
    -0.14
     proceeding
    -0.14
     greatness
    -0.13
    iem
    -0.13
    èn
    -0.13
    mux
    -0.13
    hood
    -0.13
    POSITIVE LOGITS
    -grand
    0.25
    s
    0.19
    GOR
    0.18
    sword
    0.17
    (er
    0.17
    achten
    0.16
    -gnu
    0.15
    ÏĤ
    0.15
    -quality
    0.15
    TRS
    0.15
    Act Density 0.037%

    No Known Activations