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

    Neuronpedia

    INDEX
    Explanations

    prominent numerical values and their relationships within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.69
    transQ
    -0.67
     braccia
    -0.65
    webElement
    -0.65
     GenerationType
    -0.64
     noDo
    -0.64
    }))
    -0.61
    UnsafeEnabled
    -0.60
    pushFollow
    -0.60
    >{@
    -0.59
    POSITIVE LOGITS
      (
    0.71
    enumi
    0.68
    ]='\
    0.62
    ########.
    0.61
    ]--;
    0.59
    sue
    0.58
    &=&
    0.58
    /~
    0.58
     fold
    0.57
    pital
    0.57
    Act Density 0.525%

    No Known Activations