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

    Neuronpedia

    INDEX
    Explanations

    references to publications and related documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yle
    -0.17
    -fw
    -0.16
    _CRYPTO
    -0.14
    apo
    -0.14
    anim
    -0.14
    \<^
    -0.14
    vell
    -0.14
    çģ£
    -0.14
    rames
    -0.14
    enschaft
    -0.14
    POSITIVE LOGITS
    Ðŀд
    0.15
    inx
    0.15
    immel
    0.15
     Wheeler
    0.15
     Peg
    0.15
     Sole
    0.14
     Roz
    0.14
    ismet
    0.14
    мена
    0.14
    kiem
    0.14
    Act Density 0.007%

    No Known Activations