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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possibility to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hew
    -0.36
    boneca
    -0.35
     Verantwortung
    -0.34
    protetor
    -0.33
     missione
    -0.33
     lección
    -0.33
    écou
    -0.33
     Infór
    -0.33
     Artículos
    -0.32
     épreuve
    -0.32
    POSITIVE LOGITS
     Possibility
    0.94
     possibility
    0.88
     possible
    0.86
    Possibility
    0.86
    possibility
    0.85
     possibilité
    0.82
     Possible
    0.82
     possibile
    0.81
     möglich
    0.80
    possible
    0.79
    Act Density 0.025%

    No Known Activations