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

    Neuronpedia

    INDEX
    Explanations

    phrases related to claiming ownership or making bold statements

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to stake" and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.73
    cffffcc
    -0.70
    ã
    -0.65
    irlf
    -0.65
     triangle
    -0.64
     DRAG
    -0.63
    tnc
    -0.62
     Celest
    -0.59
    =-=-=-=-=-=-=-=-
    -0.59
    isance
    -0.59
    POSITIVE LOGITS
    holders
    1.04
    holder
    0.85
    helm
    0.82
    iasis
    0.73
    warts
    0.70
    pole
    0.70
    herer
    0.68
    elist
    0.68
    kered
    0.68
    ru
    0.67
    Act Density 0.054%

    No Known Activations