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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating acknowledgment or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    |}{\
    -0.62
     wynosi
    -0.62
     PMID
    -0.55
     }{\
    -0.51
    uggling
    -0.51
    mployment
    -0.50
    XF
    -0.50
    zania
    -0.50
     lâm
    -0.49
    --
    -0.49
    POSITIVE LOGITS
    følgelig
    1.22
     course
    1.10
    verständlich
    1.06
     COURSE
    0.98
     Natürlich
    0.97
    course
    0.96
    ürlich
    0.92
    Natürlich
    0.91
    mybatisplus
    0.89
     Course
    0.87
    Act Density 0.066%

    No Known Activations