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

    Neuronpedia

    INDEX
    Explanations

    references to user interface elements in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.17
    ãĥ¼ãĥĢ
    -0.17
    hcp
    -0.16
    ibli
    -0.15
    agara
    -0.14
    uito
    -0.14
    uther
    -0.14
    ittel
    -0.14
     stan
    -0.14
     handleClose
    -0.14
    POSITIVE LOGITS
    avenport
    0.14
    äm
    0.14
     Legion
    0.14
    ;amp
    0.14
    eline
    0.14
    jen
    0.13
     Webb
    0.13
    ayar
    0.13
    ILON
    0.13
    AVIS
    0.13
    Act Density 0.002%

    No Known Activations