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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or purpose in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.56
     SwitchCompat
    -0.47
     cliquant
    -0.46
     nakalista
    -0.45
     cantando
    -0.43
     chrétien
    -0.42
    msgTypes
    -0.42
     pidiendo
    -0.41
    styleUrls
    -0.41
    horabuena
    -0.40
    POSITIVE LOGITS
     take
    1.45
     make
    1.40
     give
    1.32
     create
    1.29
     be
    1.28
     develop
    1.24
     get
    1.23
     bring
    1.23
     provide
    1.23
     execute
    1.22
    Act Density 3.008%

    No Known Activations