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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.59
    куда
    -0.55
     …
    -0.54
    ління
    -0.53
    ταν
    -0.53
    CROSSTALK
    -0.52
     חיצוניים
    -0.51
    REME
    -0.51
    riculum
    -0.50
    oretical
    -0.49
    POSITIVE LOGITS
    })*/
    0.61
     Polity
    0.61
     reaſon
    0.59
     Persia
    0.58
     reafon
    0.58
    -------
    0.57
     Bauhaus
    0.57
    modelBuilder
    0.57
     becauſe
    0.56
    )":
    0.54
    Act Density 0.649%

    No Known Activations