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

    Neuronpedia

    INDEX
    Explanations

    references to angels and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lland
    -0.17
    .Expressions
    -0.17
    ãĥĬãĥ«
    -0.16
    142
    -0.14
     κοι
    -0.14
    Å¡ak
    -0.14
    ÏĦÏİ
    -0.13
    izzo
    -0.13
    hci
    -0.13
    atra
    -0.13
    POSITIVE LOGITS
     angel
    0.66
     Angel
    0.62
     angels
    0.60
    angel
    0.60
     Angels
    0.58
    Angel
    0.56
    ang
    0.55
     angles
    0.53
    Ang
    0.51
    ANG
    0.50
    Act Density 0.127%

    No Known Activations