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

    Neuronpedia

    INDEX
    Explanations

    phrases related to failure or errors

    oai_token-act-pair · gpt-3.5-turbo

    words related to failure or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.81
    İĭ
    -0.74
    ĵĺ
    -0.72
    orers
    -0.71
    ©¶æ
    -0.70
    riber
    -0.70
    axter
    -0.70
     ende
    -0.69
     unden
    -0.67
    prises
    -0.65
    POSITIVE LOGITS
    nah
    0.85
    uminati
    0.79
    DEN
    0.71
    umbai
    0.70
     burner
    0.70
     Nadu
    0.69
    aint
    0.68
    umin
    0.67
    ptin
    0.66
    ung
    0.65
    Act Density 0.059%

    No Known Activations