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

    Neuronpedia

    INDEX
    Explanations

    words related to cleaning or clearing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "clean" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.70
     disparate
    -0.68
     Galaxy
    -0.65
    istas
    -0.65
    icum
    -0.62
    ties
    -0.62
    owitz
    -0.60
    hips
    -0.58
    ista
    -0.57
     concept
    -0.56
    POSITIVE LOGITS
    veland
    1.15
    arest
    1.05
    lean
    0.95
    llan
    0.93
    cle
    0.91
    xit
    0.88
    asure
    0.84
    arp
    0.78
    mson
    0.76
    arer
    0.76
    Act Density 0.007%

    No Known Activations