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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or political pardons and the concept of raising issues or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atories
    -0.16
    bsp
    -0.15
    ãĤ¤ãĥ¤
    -0.15
    éré
    -0.15
     NAN
    -0.15
    .intent
    -0.14
    åĢ
    -0.14
     KiÅŁ
    -0.14
    irsch
    -0.14
    ATEST
    -0.13
    POSITIVE LOGITS
    ons
    0.80
    ONS
    0.56
    on
    0.55
    ón
    0.52
    ON
    0.51
    oned
    0.50
    он
    0.49
    onn
    0.48
    ÙĪÙĨ
    0.48
    oning
    0.46
    Act Density 0.072%

    No Known Activations