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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters indicating non-standard text formatting or annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤŃãĥ¥
    -0.15
     Edgar
    -0.14
    efs
    -0.14
    sy
    -0.14
     Ngh
    -0.14
    имÑĥ
    -0.14
    imas
    -0.14
    aded
    -0.13
     flakes
    -0.13
    edl
    -0.13
    POSITIVE LOGITS
    pag
    0.15
    ç¾
    0.14
    antar
    0.13
    VD
    0.13
    opup
    0.13
    UPI
    0.13
     benchmarks
    0.13
     withholding
    0.13
    rage
    0.13
    .Mutable
    0.13
    Act Density 0.016%

    No Known Activations