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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vermögen
    -0.53
     Leip
    -0.47
    まさに
    -0.47
    Loyalty
    -0.47
    Ors
    -0.47
    ORN
    -0.47
    еремо
    -0.46
     réputation
    -0.46
     keres
    -0.46
    ेर
    -0.46
    POSITIVE LOGITS
     okay
    1.78
     alright
    1.75
     OK
    1.68
     OKAY
    1.60
     ok
    1.59
     Alright
    1.56
    alright
    1.56
    okay
    1.52
     Okay
    1.46
    Okay
    1.46
    Act Density 0.224%

    No Known Activations