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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate removal or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erras
    -0.16
    juan
    -0.15
     Harmony
    -0.15
    uarios
    -0.15
    uario
    -0.15
    Ā
    -0.14
    474
    -0.14
    .userData
    -0.14
    ither
    -0.14
    rog
    -0.14
    POSITIVE LOGITS
    rah
    0.17
     exact
    0.17
     Exact
    0.17
    obao
    0.15
     khá»ıi
    0.15
    summ
    0.15
    exact
    0.15
    que
    0.15
    ä¸ĢæŃ¥
    0.14
    iginal
    0.14
    Act Density 0.149%

    No Known Activations