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

    Neuronpedia

    INDEX
    Explanations

    diacritical marks in words, particularly in non-English languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.17
    ت
    -0.15
    fal
    -0.14
    aru
    -0.14
    ialis
    -0.14
    160
    -0.14
    ãĤ¾
    -0.14
    ens
    -0.14
    274
    -0.13
    indo
    -0.13
    POSITIVE LOGITS
    ryo
    0.15
    ogi
    0.15
    çĩ
    0.14
    eum
    0.14
    raits
    0.14
    abant
    0.14
    acle
    0.14
    signature
    0.14
    appy
    0.14
    elocity
    0.14
    Act Density 0.011%

    No Known Activations