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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases indicating uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ador
    -0.16
    ADOR
    -0.15
    avra
    -0.15
    apse
    -0.15
    ERG
    -0.14
    adık
    -0.14
     Bened
    -0.14
    Âŀ
    -0.14
     बय
    -0.14
    ìĦŃ
    -0.14
    POSITIVE LOGITS
     Norm
    0.18
    èĻ
    0.15
     Earl
    0.14
     branch
    0.14
     Name
    0.14
     Rod
    0.14
     cg
    0.14
    ãĥĪãĥª
    0.14
     CG
    0.14
    addle
    0.13
    Act Density 0.001%

    No Known Activations