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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing strong opinions or complaints

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vocalization and proliferation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sw
    -0.70
     thinking
    -0.67
     breakfast
    -0.64
     Vertical
    -0.62
     traditional
    -0.61
     boarding
    -0.61
     simplified
    -0.61
     parties
    -0.60
    home
    -0.60
     precision
    -0.60
    POSITIVE LOGITS
    ifer
    4.89
    iferation
    1.50
    ifier
    1.21
    if
    1.18
    ific
    1.13
    ifiers
    1.09
    IFIED
    1.09
    IFIC
    1.08
    ife
    1.08
    ifies
    1.02
    Act Density 0.009%

    No Known Activations