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

    Neuronpedia

    INDEX
    Explanations

    references to consistent or persistent themes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĶ
    -0.15
    erot
    -0.15
    lesh
    -0.15
    elson
    -0.14
    iÄĻ
    -0.14
    lobs
    -0.14
    hoot
    -0.14
    .mozilla
    -0.13
    erson
    -0.13
    rema
    -0.13
    POSITIVE LOGITS
    aneous
    0.18
    aneously
    0.15
    AGR
    0.15
    wy
    0.14
    akis
    0.14
    деÑĢ
    0.14
    une
    0.13
    ovnÄĽ
    0.13
     scaff
    0.13
    axed
    0.13
    Act Density 0.021%

    No Known Activations