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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quip
    -0.18
    GridColumn
    -0.17
    ãĤīãģĦ
    -0.17
    ica
    -0.15
    ãĥ«ãĥī
    -0.15
    Arena
    -0.15
    olding
    -0.15
    _SHA
    -0.14
    quito
    -0.14
    mony
    -0.14
    POSITIVE LOGITS
     Chop
    0.16
    oeff
    0.16
    opol
    0.15
     inst
    0.15
     Bob
    0.15
    arton
    0.15
    ison
    0.15
     imm
    0.15
    imm
    0.14
     secret
    0.14
    Act Density 0.016%

    No Known Activations