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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to measurements or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Barr
    -0.66
    marvin
    -0.66
    **************
    -0.66
     SM
    -0.65
     Silverman
    -0.64
     HasFactory
    -0.64
     Franco
    -0.64
    برا
    -0.62
    脚注の使い方
    -0.59
     ministère
    -0.59
    POSITIVE LOGITS
     propOrder
    0.96
     useCallback
    0.83
    fjspx
    0.79
    ❋
    0.77
     porridge
    0.77
     Coolidge
    0.77
     coils
    0.77
    endphp
    0.77
     pooh
    0.76
    Попис
    0.76
    Act Density 0.655%

    No Known Activations