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

    Neuronpedia

    INDEX
    Explanations

    references to allegations and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idge
    -0.18
    upt
    -0.18
    ãĤīãģļ
    -0.15
    ehler
    -0.15
    roe
    -0.15
    lle
    -0.15
    vr
    -0.14
    icens
    -0.14
    angler
    -0.14
    hee
    -0.14
    POSITIVE LOGITS
    /problem
    0.16
    antium
    0.15
    cce
    0.14
    /request
    0.14
     Moon
    0.14
    kara
    0.14
    /question
    0.13
     against
    0.13
    óc
    0.13
    airs
    0.13
    Act Density 0.036%

    No Known Activations