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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    C
    -0.17
    p
    -0.16
    H
    -0.16
    aching
    -0.15
    T
    -0.14
    ä¹İ
    -0.14
    ductor
    -0.14
    D
    -0.14
    636
    -0.14
     Fres
    -0.14
    POSITIVE LOGITS
    podob
    0.21
     means
    0.19
    ãĥ³ãĥķ
    0.17
    means
    0.15
    ahir
    0.15
    atches
    0.15
    ãģªãģĮ
    0.14
    tel
    0.14
    ecycle
    0.14
     way
    0.14
    Act Density 0.088%

    No Known Activations