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

    Neuronpedia

    INDEX
    Explanations

    phrases or content indicating structured guidance or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    501
    -0.15
    _
    -0.15
    523
    -0.15
    abar
    -0.14
    uke
    -0.14
    ลำ
    -0.14
     Outside
    -0.14
     Johnston
    -0.13
     virgin
    -0.13
    amar
    -0.13
    POSITIVE LOGITS
    atatype
    0.17
    íĨłíĨł
    0.15
    æĺĩ
    0.15
    .Xaml
    0.15
     müc
    0.15
    icamente
    0.14
    ooter
    0.14
    ëį°ìĿ´íĬ¸
    0.14
    uffs
    0.14
    iffs
    0.14
    Act Density 0.062%

    No Known Activations