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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups or categories that start with "these."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     αÏħÏĦή
    -0.17
    ation
    -0.15
     uz
    -0.14
    dest
    -0.14
    ãĥ³ãĥĦ
    -0.14
    liest
    -0.14
    ica
    -0.14
    о
    -0.13
    ìłģ
    -0.13
    odal
    -0.13
    POSITIVE LOGITS
    curity
    0.29
    quence
    0.26
     kinds
    0.25
    verity
    0.25
     sorts
    0.24
    cond
    0.24
     same
    0.22
     guys
    0.22
    /th
    0.20
     days
    0.20
    Act Density 0.091%

    No Known Activations