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

    Neuronpedia

    INDEX
    Explanations

    terms related to change and transformation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AFE
    -0.15
    Closure
    -0.15
    urat
    -0.14
    orgia
    -0.14
    chts
    -0.14
    landa
    -0.14
    #af
    -0.14
    omain
    -0.14
    udies
    -0.13
    rouw
    -0.13
    POSITIVE LOGITS
     how
    0.29
     way
    0.28
    how
    0.23
     parad
    0.23
     traditional
    0.23
     ways
    0.22
     HOW
    0.21
     approach
    0.20
    å¦Ĥä½ķ
    0.20
     cách
    0.20
    Act Density 0.150%

    No Known Activations