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

    Neuronpedia

    INDEX
    Explanations

    references to Donald Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldorf
    -0.18
    ANO
    -0.16
    ingga
    -0.15
    ed
    -0.15
    VML
    -0.15
    çķ
    -0.14
    iola
    -0.14
    iling
    -0.14
    letics
    -0.14
    @qq
    -0.14
    POSITIVE LOGITS
    son
    0.21
    ization
    0.21
    ized
    0.20
    sons
    0.19
    sson
    0.19
    ismus
    0.18
    ised
    0.18
    wealth
    0.16
    SON
    0.16
    ocoder
    0.16
    Act Density 0.016%

    No Known Activations