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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure indicating the end of functions or blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apan
    -0.15
     Erd
    -0.15
    ankan
    -0.15
    /goto
    -0.15
    ekt
    -0.14
    çĵ¦
    -0.14
    妮
    -0.14
    æĸ½
    -0.13
    ajo
    -0.13
    arme
    -0.13
    POSITIVE LOGITS
    alon
    0.16
     cad
    0.15
    oubted
    0.15
    _UNUSED
    0.14
    ánh
    0.14
    Ñijм
    0.13
     Unused
    0.13
     sil
    0.13
    ysql
    0.13
     unused
    0.13
    Act Density 0.004%

    No Known Activations