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

    Neuronpedia

    INDEX
    Explanations

    expressions related to actions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enan
    -0.15
    민
    -0.15
     Zi
    -0.15
    .WinForms
    -0.14
    arel
    -0.14
    icter
    -0.13
    AIT
    -0.13
     helicopt
    -0.13
    forder
    -0.13
    ango
    -0.13
    POSITIVE LOGITS
     Vak
    0.16
    deen
    0.16
     av
    0.14
    ī´
    0.14
     Ruf
    0.14
    gee
    0.14
     nov
    0.14
    chant
    0.13
    inct
    0.13
    erli
    0.13
    Act Density 0.014%

    No Known Activations