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

    Neuronpedia

    INDEX
    Explanations

    expressions of thought and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.16
    lements
    -0.15
    ytt
    -0.14
    noDB
    -0.14
    oris
    -0.14
    hread
    -0.14
     Royal
    -0.14
    eres
    -0.13
    ometr
    -0.13
    _OS
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĸãĥ«
    0.15
    oad
    0.15
     til
    0.15
     Pump
    0.14
    hof
    0.14
    erville
    0.14
     surely
    0.13
     Titanium
    0.13
     absor
    0.13
     phen
    0.13
    Act Density 0.162%

    No Known Activations