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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SYS
    -0.15
    ingu
    -0.15
    ãĥ¼ãĤ¹ãĥĪ
    -0.14
    adan
    -0.14
     hist
    -0.14
    ippi
    -0.13
    Ñħи
    -0.13
    OTA
    -0.13
     vmin
    -0.13
    åĦĢ
    -0.13
    POSITIVE LOGITS
    ä¹ĥ
    0.15
     aks
    0.14
    /renderer
    0.14
    loquent
    0.14
     Wet
    0.14
    uilder
    0.13
     trop
    0.13
    battle
    0.13
    arte
    0.13
     wid
    0.13
    Act Density 0.007%

    No Known Activations