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

    Neuronpedia

    INDEX
    Explanations

    references to specific issues or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tera
    -0.16
     Crane
    -0.15
    lez
    -0.14
    vey
    -0.14
    -tab
    -0.14
    arga
    -0.14
    plat
    -0.14
     recap
    -0.14
    ahrain
    -0.14
    itti
    -0.14
    POSITIVE LOGITS
     apl
    0.15
     snap
    0.15
    aju
    0.14
     choke
    0.14
    obot
    0.14
    ufac
    0.14
     "-";↵
    0.14
    essler
    0.14
    clud
    0.13
    oton
    0.13
    Act Density 0.109%

    No Known Activations