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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating clarity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.77
    sidemargin
    -0.56
     Paxton
    -0.56
    dess
    -0.56
     Arm
    -0.55
    oult
    -0.55
     Bevan
    -0.55
     PRACTICES
    -0.54
     Lovell
    -0.54
    intersect
    -0.54
    POSITIVE LOGITS
     clearly
    3.50
    clearly
    3.23
     Clearly
    3.01
    Clearly
    2.83
     claramente
    2.48
     clairement
    2.29
     chiaramente
    2.25
     duidelijk
    1.95
     plainly
    1.88
     CLEAR
    1.73
    Act Density 0.094%

    No Known Activations