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

    Neuronpedia

    INDEX
    Explanations

    the verb "perform" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.90
    AsUp
    -0.66
     Италијани
    -0.66
    KEYCODE
    -0.66
    IVEREF
    -0.66
     BorderRadius
    -0.64
    oubted
    -0.63
    ])+
    -0.63
    etheless
    -0.63
    ocity
    -0.63
    POSITIVE LOGITS
     perform
    3.03
     performed
    2.94
     Perform
    2.91
     performing
    2.84
     PERFORM
    2.73
    Perform
    2.73
     performs
    2.69
     Performing
    2.62
    perform
    2.60
     Performed
    2.54
    Act Density 0.153%

    No Known Activations