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

    Neuronpedia

    INDEX
    Explanations

    actions related to cleaning or removing substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.72
     scatola
    -0.65
    findpost
    -0.64
    RegisterType
    -0.64
     empress
    -0.59
     cleats
    -0.59
    cahontas
    -0.58
     subsidies
    -0.58
    hawatir
    -0.57
     Compli
    -0.56
    POSITIVE LOGITS
     Wipe
    0.84
     wipe
    0.84
     wipes
    0.82
    Wipe
    0.80
    wipe
    0.78
     tartalomajánló
    0.77
     wiped
    0.76
     wiping
    0.75
     pleasant
    0.75
     Wiktionnaire
    0.73
    Act Density 0.403%

    No Known Activations