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

    Neuronpedia

    INDEX
    Explanations

    words that express a sense of approximation or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PMailer
    -0.70
     Erb
    -0.69
    LookAnd
    -0.66
     solen
    -0.66
    -0.65
     polaire
    -0.65
    ContentAlignment
    -0.65
     Mell
    -0.65
     chi̍t
    -0.65
    dillera
    -0.65
    POSITIVE LOGITS
     oeufs
    0.90
     Shimizu
    0.88
     Mumford
    0.88
     ApiService
    0.82
     Niki
    0.81
     SHOP
    0.81
    theless
    0.80
    >>>>>>>
    0.80
    ̀u
    0.79
     Nuk
    0.78
    Act Density 0.047%

    No Known Activations