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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate methods or means to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angelo
    -0.07
    lek
    -0.07
    gram
    -0.07
    áj
    -0.07
    pedo
    -0.07
    ated
    -0.07
    atern
    -0.07
    him
    -0.07
    ordin
    -0.07
    itag
    -0.07
    POSITIVE LOGITS
    urement
    0.10
    owment
    0.07
    ród
    0.07
    orem
    0.06
    isters
    0.06
    ings
    0.06
    pir
    0.06
    ìłĢ
    0.06
    ãĢħ
    0.06
    .fm
    0.06
    Act Density 0.011%

    No Known Activations