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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a type or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     volontà
    -0.60
     colère
    -0.59
     suficientes
    -0.57
     ragioni
    -0.56
     piú
    -0.56
    many
    -0.56
     atât
    -0.54
    several
    -0.54
     medesimo
    -0.54
     essenziale
    -0.54
    POSITIVE LOGITS
    "):
    0.96
    ratulations
    0.90
    ^(@)
    0.90
     thing
    0.88
    uesday
    0.85
    )':
    0.85
    }}]{
    0.84
     relationship
    0.84
    )":
    0.84
    olesale
    0.84
    Act Density 0.209%

    No Known Activations