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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting audience engagement and personal evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stÃŃ
    -0.16
    aper
    -0.15
    reek
    -0.15
    igne
    -0.15
    erno
    -0.15
     whim
    -0.15
    úc
    -0.14
     Quest
    -0.14
    ost
    -0.14
    asa
    -0.14
    POSITIVE LOGITS
     judge
    0.23
     yourself
    0.22
     for
    0.21
     yourselves
    0.20
    for
    0.19
    _for
    0.19
     themselves
    0.18
     ÑģобÑĸ
    0.18
     Yourself
    0.18
    judge
    0.18
    Act Density 0.036%

    No Known Activations