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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canf
    -0.19
    iaux
    -0.18
    ête
    -0.17
    vetica
    -0.16
    avadoc
    -0.16
    rete
    -0.15
    raquo
    -0.15
    adele
    -0.15
    repos
    -0.15
    dale
    -0.15
    POSITIVE LOGITS
    atom
    0.15
    621
    0.15
    ored
    0.14
    ully
    0.14
     Charm
    0.14
    ìĽĥ
    0.14
    atum
    0.14
    on
    0.14
     Mir
    0.14
     atom
    0.13
    Act Density 0.004%

    No Known Activations