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

    Neuronpedia

    INDEX
    Explanations

    statements pertaining to accountability and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !
    -1.02
     our
    -0.98
     we
    -0.84
    !)
    -0.83
     my
    -0.82
    !!!
    -0.81
    !),
    -0.80
     нами
    -0.80
    !!
    -0.79
     нам
    -0.77
    POSITIVE LOGITS
     pihaknya
    1.31
    parsedMessage
    1.06
    RegressionTest
    1.05
    ApiModelProperty
    1.03
     müsse
    1.01
     könne
    0.97
    SourceChecksum
    0.96
     seien
    0.93
    featureID
    0.90
    ItemBackground
    0.90
    Act Density 0.332%

    No Known Activations