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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating controversy or public reaction to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.25
    ⓧ
    -0.66
     underval
    -0.47
     enrich
    -0.47
     Assays
    -0.46
     Decorate
    -0.46
    achieve
    -0.46
     endwhile
    -0.45
    <?
    -0.44
     hisz
    -0.44
    POSITIVE LOGITS
     Muhamma
    1.13
     Minang
    1.02
     Jambi
    0.96
     Khart
    0.95
     Palembang
    0.93
     Keny
    0.93
     smtplib
    0.92
     Juf
    0.92
     Banjar
    0.92
     Nusantara
    0.91
    Act Density 0.499%

    No Known Activations