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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote success or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.15
    ephir
    -0.14
    ustum
    -0.14
    occan
    -0.14
    ãĤ©
    -0.13
    ahy
    -0.13
    vinces
    -0.13
    392
    -0.13
    ĵn
    -0.13
    urations
    -0.13
    POSITIVE LOGITS
    ÏģοÏį
    0.14
    ibu
    0.14
    forth
    0.13
    lever
    0.13
    ERO
    0.13
     hence
    0.13
    kte
    0.13
     çünkü
    0.13
    chers
    0.13
    reply
    0.12
    Act Density 0.070%

    No Known Activations