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

    Neuronpedia

    INDEX
    Explanations

    phrases related to waiting or deferring actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.69
    endphp
    -0.67
    MergeFrom
    -0.65
    AutoresizingMask
    -0.61
    хьтан
    -0.59
    GIVEREF
    -0.58
     astore
    -0.57
    PreExecute
    -0.57
    (:,:,
    -0.55
     perpetuity
    -0.55
    POSITIVE LOGITS
     wait
    0.79
     waited
    0.74
     delay
    0.68
     waiting
    0.63
     Wait
    0.59
    wait
    0.56
     delayed
    0.55
     waits
    0.55
     WAIT
    0.52
    delay
    0.52
    Act Density 0.143%

    No Known Activations