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

    Neuronpedia

    INDEX
    Explanations

    references to trust and related concepts in the context of risk or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lum
    -0.17
     Lum
    -0.16
    arity
    -0.16
     elsewhere
    -0.15
    kan
    -0.15
    ÙĦÙĬÙĩ
    -0.15
     spo
    -0.15
    iar
    -0.15
    iat
    -0.15
    oir
    -0.14
    POSITIVE LOGITS
    AFX
    0.15
    &o
    0.15
    idth
    0.15
    Wunused
    0.15
    NotAllowed
    0.14
    #ad
    0.14
    ãĤ±ãĥ¼ãĤ¹
    0.14
    outu
    0.13
     ud
    0.13
    .scalablytyped
    0.13
    Act Density 0.015%

    No Known Activations