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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or comprehension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.58
     AssemblyTitle
    -0.54
    Ђ
    -0.53
    __":
    -0.52
    __':
    -0.52
     الحره
    -0.51
    tiérrez
    -0.50
    geführt
    -0.49
    formis
    -0.49
    tille
    -0.48
    POSITIVE LOGITS
    WriteAttribute
    0.68
    guenos
    0.67
     knows
    0.66
     conozco
    0.65
     tudom
    0.64
     know
    0.64
    BeginContext
    0.64
     IconData
    0.63
    我知道
    0.63
     understands
    0.62
    Act Density 0.112%

    No Known Activations