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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical relations and properties of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    almaz
    -0.55
    UnusedPrivate
    -0.55
    fony
    -0.54
    Alike
    -0.51
    ėmis
    -0.51
     braccia
    -0.50
    endphp
    -0.49
    AndEndTag
    -0.49
     updatedAt
    -0.49
    ArgumentParser
    -0.48
    POSITIVE LOGITS
    lerinin
    0.90
    larının
    0.83
    ının
    0.80
    ünün
    0.79
    ğın
    0.74
    ların
    0.72
     insanların
    0.72
    idän
    0.69
    ⓧ
    0.69
    ın
    0.67
    Act Density 0.292%

    No Known Activations