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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting a minimum quantity or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdx
    -0.66
     invece
    -0.65
     exactement
    -0.65
     justru
    -0.63
     exactly
    -0.60
    exactly
    -0.59
     exactamente
    -0.59
    UnusedPrivate
    -0.58
     exatamente
    -0.58
    Exactly
    -0.57
    POSITIVE LOGITS
     partially
    1.08
     partly
    0.98
     partial
    0.93
     Partially
    0.90
     parcialmente
    0.89
    partly
    0.86
     Partial
    0.83
    parti
    0.82
     partiellement
    0.81
    Partial
    0.80
    Act Density 0.194%

    No Known Activations