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

    Neuronpedia

    INDEX
    Explanations

    words related to descriptions or explanatory text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    penup
    -0.77
    Wiel
    -0.75
    Theorem
    -0.75
     gặp
    -0.74
    Amicalement
    -0.72
    __':
    -0.71
    THEOREM
    -0.70
     Theorem
    -0.68
     aient
    -0.68
     Brodie
    -0.66
    POSITIVE LOGITS
     description
    2.21
    Description
    2.08
     Description
    2.03
     descriptions
    2.02
    description
    2.01
    DESCRIPTION
    1.84
     DESCRIPTION
    1.80
    getDescription
    1.78
    setDescription
    1.73
     descrip
    1.70
    Act Density 0.062%

    No Known Activations