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

    Neuronpedia

    INDEX
    Explanations

    terms relevant to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pratique
    -0.79
    MLLoader
    -0.75
    verläs
    -0.66
    dengar
    -0.65
    poptosis
    -0.65
    Personendaten
    -0.62
    ELTS
    -0.60
     autorytatywna
    -0.59
    orexia
    -0.59
    ategorien
    -0.58
    POSITIVE LOGITS
    aria
    0.75
    ics
    0.68
    ary
    0.67
    aries
    0.66
    ery
    0.64
    ory
    0.64
    toxicity
    0.63
    mut
    0.63
    ARY
    0.61
    iterator
    0.59
    Act Density 2.115%

    No Known Activations