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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intentions and plans for future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cac
    -0.54
     huyền
    -0.48
    amazonaws
    -0.47
    ulaski
    -0.46
    ọc
    -0.46
     vytvá
    -0.45
     môi
    -0.45
    cendental
    -0.45
    Leggi
    -0.45
    izaje
    -0.44
    POSITIVE LOGITS
     plans
    1.54
    plans
    1.30
     Plans
    1.28
     intentions
    1.26
     planned
    1.26
    Plans
    1.22
     intends
    1.22
     PLANS
    1.20
     Pläne
    1.20
     plan
    1.16
    Act Density 0.229%

    No Known Activations