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

    Neuronpedia

    INDEX
    Explanations

    elements indicating uncertainty or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ideon
    -0.18
    edula
    -0.16
     Gaut
    -0.15
     Wagner
    -0.15
    okud
    -0.14
    ingo
    -0.14
    \.
    -0.13
     si
    -0.13
    PublicKey
    -0.13
    irection
    -0.13
    POSITIVE LOGITS
     доб
    0.19
    onavir
    0.17
    idor
    0.15
    ovah
    0.15
    rrha
    0.15
    drm
    0.14
    åijĢ
    0.14
    buat
    0.14
    enas
    0.14
    retty
    0.14
    Act Density 0.002%

    No Known Activations