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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duration or circularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.16
     Pall
    -0.15
     Radical
    -0.15
    weis
    -0.15
     DISP
    -0.14
    atr
    -0.14
    asl
    -0.14
    athe
    -0.14
    ainer
    -0.13
     Pal
    -0.13
    POSITIVE LOGITS
    _testing
    0.15
     dil
    0.14
    428
    0.14
    ysa
    0.14
    .uni
    0.14
    YTE
    0.13
    -го
    0.13
    otton
    0.13
    Hel
    0.13
     Pars
    0.13
    Act Density 0.019%

    No Known Activations