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

    Neuronpedia

    INDEX
    Explanations

    negative values or terms indicating negativity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tpl
    -0.66
     Sexton
    -0.63
     Contributions
    -0.60
     Contribution
    -0.60
    playable
    -0.59
    >+</
    -0.58
     adder
    -0.56
    )}+
    -0.56
    Contribution
    -0.55
    oneofs
    -0.55
    POSITIVE LOGITS
    -​
    0.81
     nahilalakip
    0.73
     -"
    0.70
    — 
    0.69
    ）-
    0.69
     Gurney
    0.69
    $-$
    0.67
    ه‌
    0.66
    }$-
    0.65
    /*
    0.65
    Act Density 0.069%

    No Known Activations