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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or questioning regarding feelings and interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skyt
    -0.17
    лиÑĩ
    -0.16
    arios
    -0.16
    .scalablytyped
    -0.15
    tel
    -0.15
    ÙĬÙħÙĬ
    -0.15
    TEL
    -0.15
    اراÙĨ
    -0.15
    ëĦ·
    -0.15
    .setAction
    -0.14
    POSITIVE LOGITS
    ite
    0.16
     somehow
    0.15
     Lite
    0.15
     dust
    0.14
    float
    0.14
    ìĦł
    0.14
    DAQ
    0.14
    bla
    0.14
    iyon
    0.14
     Gilles
    0.13
    Act Density 0.923%

    No Known Activations