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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ********/
    -0.52
    Сем
    -0.51
    害
    -0.48
    masing
    -0.48
     Bert
    -0.46
     Maynard
    -0.46
     الحره
    -0.46
     Seventeen
    -0.45
     Mild
    -0.45
     Fury
    -0.44
    POSITIVE LOGITS
    enterOuterAlt
    0.70
    SequentialGroup
    0.69
    AutoScaleMode
    0.67
     nakalista
    0.65
    IntoConstraints
    0.64
     Roskov
    0.61
    ]--;
    0.60
    kháu
    0.60
    apimachinery
    0.60
    AlterField
    0.59
    Act Density 0.258%

    No Known Activations