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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions and their consequences or situations being addressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymoon
    -0.17
    phy
    -0.17
    inker
    -0.15
    anzi
    -0.15
     recon
    -0.15
    ãĤ¹ãĥŀ
    -0.14
    unas
    -0.14
    planet
    -0.14
    phyl
    -0.14
    peak
    -0.14
    POSITIVE LOGITS
    oldem
    0.16
    umn
    0.16
    elman
    0.16
    _pid
    0.15
    urette
    0.14
     =========================================================================
    0.14
    æķ¦
    0.14
    olicited
    0.14
    termin
    0.14
     borough
    0.14
    Act Density 0.317%

    No Known Activations