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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    klass
    -0.18
    лем
    -0.17
    /umd
    -0.16
    ylim
    -0.15
    shots
    -0.15
    öm
    -0.15
    yms
    -0.15
    chter
    -0.15
    edly
    -0.15
    gamber
    -0.15
    POSITIVE LOGITS
    ice
    0.34
    itor
    0.31
    itors
    0.29
    vier
    0.27
    usz
    0.27
    ine
    0.26
    uar
    0.26
    et
    0.26
    eway
    0.26
    ey
    0.25
    Act Density 0.010%

    No Known Activations