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

    Neuronpedia

    INDEX
    Explanations

    instances where the term "cap" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to "cap" or "capacity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bread
    -0.70
     anten
    -0.69
    ĪĴ
    -0.69
    issance
    -0.65
    hower
    -0.64
    isance
    -0.63
     Roses
    -0.61
    cause
    -0.61
     Modes
    -0.60
     Fres
    -0.59
    POSITIVE LOGITS
    itol
    1.48
    uchin
    1.11
    aic
    1.03
    rice
    1.02
    illary
    1.01
    itals
    0.93
    stan
    0.92
    rices
    0.92
    nea
    0.92
    rison
    0.88
    Act Density 0.024%

    No Known Activations