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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eza
    -0.17
    andon
    -0.16
    един
    -0.15
     Canter
    -0.15
    ection
    -0.15
     Tie
    -0.15
    cott
    -0.14
    omor
    -0.14
    ingly
    -0.14
    ãĥ¼ãĥ
    -0.14
    POSITIVE LOGITS
     Robbins
    0.16
    iser
    0.15
     Peyton
    0.15
    fcn
    0.15
     exact
    0.15
    λία
    0.14
    loy
    0.14
     bä
    0.14
     ìŀIJë£Į
    0.14
     strap
    0.14
    Act Density 0.061%

    No Known Activations