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

    Neuronpedia

    INDEX
    Explanations

    terms associated with measuring or describing quantitative outcomes or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     riuscito
    -0.64
     aikana
    -0.53
     banget
    -0.52
     stesse
    -0.52
    czegó
    -0.51
    neiden
    -0.51
     strøm
    -0.50
     femininos
    -0.49
     sumpay
    -0.49
     esimer
    -0.49
    POSITIVE LOGITS
     become
    0.91
    become
    0.83
    ConstraintMaker
    0.82
     AssemblyCulture
    0.82
     becoming
    0.81
     being
    0.74
     unrecogn
    0.74
     diventare
    0.72
    becoming
    0.71
     ModelExpression
    0.70
    Act Density 0.400%

    No Known Activations