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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and high-frequency connecting words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rame
    -0.16
    enia
    -0.15
    [email
    -0.15
    ogie
    -0.15
    ique
    -0.14
    ored
    -0.14
    pe
    -0.14
    urg
    -0.13
    bron
    -0.13
    iao
    -0.13
    POSITIVE LOGITS
    962
    0.16
    avras
    0.16
    ugins
    0.15
    glyphicon
    0.15
    948
    0.15
    Wunused
    0.15
    DFS
    0.15
    ughter
    0.14
    andal
    0.14
     Minor
    0.14
    Act Density 0.000%

    No Known Activations