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

    Neuronpedia

    INDEX
    Explanations

    instances of surprise and unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSIP
    -0.15
    ãĥ³ãĥĩ
    -0.15
    εβ
    -0.14
    лини
    -0.14
    ponge
    -0.14
    vis
    -0.14
    iped
    -0.14
    ิà¸ķร
    -0.14
    inez
    -0.14
     rfl
    -0.14
    POSITIVE LOGITS
     Hutch
    0.16
    104
    0.16
    laden
    0.14
     surprise
    0.14
    ä»ķ
    0.14
    ufe
    0.14
    aporan
    0.13
    eka
    0.13
    103
    0.13
     lith
    0.13
    Act Density 0.173%

    No Known Activations