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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance or execution of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.82
     ingrat
    -0.80
     millennium
    -0.76
     estimés
    -0.72
    bigoplus
    -0.69
     Bucky
    -0.69
     mapStateToProps
    -0.68
    بوابة
    -0.68
     newVal
    -0.67
     Zat
    -0.66
    POSITIVE LOGITS
     performed
    1.49
     PERFORM
    1.39
    performed
    1.37
     perform
    1.35
     Perform
    1.25
    Perform
    1.23
     Performed
    1.20
    effectuer
    1.19
    perform
    1.14
     performs
    1.12
    Act Density 0.176%

    No Known Activations