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

    Neuronpedia

    INDEX
    Explanations

    specific types of objects and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saltar
    -0.81
    ſelves
    -0.78
    ]")]
    -0.73
    #
    -0.71
     ModelExpression
    -0.70
    TypedDataSet
    -0.69
    seamnă
    -0.67
    SizeMode
    -0.66
    ſelf
    -0.66
     Houſe
    -0.65
    POSITIVE LOGITS
     BorderRadius
    0.50
     Drapeau
    0.46
    esus
    0.46
    moe
    0.43
    timedelta
    0.43
    qrstuvwxyz
    0.42
     betweenstory
    0.42
    roppo
    0.41
    зонта
    0.41
     explosive
    0.40
    Act Density 0.060%

    No Known Activations