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

    Neuronpedia

    INDEX
    Explanations

    terms related to importance and criticality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alama
    -0.15
    idar
    -0.15
     Starr
    -0.15
    .avi
    -0.14
    éIJ
    -0.14
    orum
    -0.14
    asal
    -0.14
    idd
    -0.14
    ¼
    -0.14
    521
    -0.13
    POSITIVE LOGITS
    éru
    0.16
    loor
    0.16
    onto
    0.15
    imagin
    0.15
    ynet
    0.14
    dale
    0.14
    rsa
    0.14
    POSITE
    0.14
    eldon
    0.14
    Å¡li
    0.14
    Act Density 0.248%

    No Known Activations