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

    Neuronpedia

    INDEX
    Explanations

    references to additional items or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ha
    -0.07
    vecs
    -0.07
     Slot
    -0.06
    важа
    -0.06
    )(_
    -0.06
     Carr
    -0.06
     Tre
    -0.06
    okable
    -0.06
    ibri
    -0.06
    .)↵↵↵↵
    -0.06
    POSITIVE LOGITS
    etc
    0.07
    Ĭ
    0.07
    zens
    0.07
    others
    0.06
     Rena
    0.06
    ewire
    0.06
    alli
    0.06
     rej
    0.06
    HORT
    0.06
     nữa
    0.06
    Act Density 0.002%

    No Known Activations