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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or requirements for various actions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.53
     ovviamente
    -0.51
    InvalidProtocol
    -0.49
    rootScope
    -0.48
    гән
    -0.48
     yaptığı
    -0.47
     ddelweddau
    -0.46
     basically
    -0.45
     
    -0.44
    стоян
    -0.44
    POSITIVE LOGITS
    anskje
    0.92
    WebVitals
    0.88
     may
    0.87
    もしれません
    0.85
     misschien
    0.84
     vielleicht
    0.81
     might
    0.81
     disambiguazione
    0.79
     itſelf
    0.78
     ainfi
    0.77
    Act Density 0.752%

    No Known Activations