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

    Neuronpedia

    INDEX
    Explanations

    phrases related to features or characteristics of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.70
     perſon
    -0.67
    IsContent
    -0.67
     faptul
    -0.67
     nôtre
    -0.66
    IntoConstraints
    -0.65
     houſe
    -0.64
     Jefus
    -0.62
     myſelf
    -0.61
     cauſe
    -0.61
    POSITIVE LOGITS
    holds
    0.73
    stood
    0.70
     a
    0.68
    RunWith
    0.61
     no
    0.60
    standing
    0.59
     distinctive
    0.57
     its
    0.57
     two
    0.56
    with
    0.56
    Act Density 0.314%

    No Known Activations