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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to actions and their impacts or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    och
    -0.18
    eb
    -0.17
    their
    -0.16
    ox
    -0.15
    Ñı
    -0.15
    um
    -0.15
    ik
    -0.15
    athi
    -0.15
    ãģ¨ãģĹãģŁ
    -0.15
    oth
    -0.15
    POSITIVE LOGITS
    isque
    0.16
     itself
    0.15
    lique
    0.14
    uars
    0.14
    lick
    0.14
    licken
    0.14
    redo
    0.14
    ngle
    0.14
    dü
    0.14
    /***/
    0.14
    Act Density 0.846%

    No Known Activations