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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future plans or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    навли
    -0.65
    Искәрмәләр
    -0.63
    شهاد
    -0.53
    Diweddarwch
    -0.52
     approaching
    -0.52
     bezeichneter
    -0.51
     kasarigan
    -0.49
    Moss
    -0.47
    Kjelder
    -0.47
    IsMutable
    -0.47
    POSITIVE LOGITS
     stay
    3.02
     stays
    2.80
     Stay
    2.73
     stayed
    2.73
    stay
    2.73
     remain
    2.67
    Stay
    2.56
     staying
    2.54
     remained
    2.48
     STAY
    2.46
    Act Density 0.556%

    No Known Activations