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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate placing or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whigs
    -0.96
     scolaires
    -0.93
     Мексичка
    -0.89
    rawDesc
    -0.87
     scrubber
    -0.86
    rrggbb
    -0.84
    تفصیلات
    -0.82
    __':
    -0.82
    JNIEnv
    -0.81
     Ouro
    -0.81
    POSITIVE LOGITS
     placed
    1.50
     placing
    1.30
     place
    1.30
    Placed
    1.30
     placement
    1.24
    Place
    1.23
     PLAC
    1.23
    place
    1.22
     Place
    1.20
    placed
    1.20
    Act Density 0.016%

    No Known Activations