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

    Neuronpedia

    INDEX
    Explanations

    terms related to misinformation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jen
    -0.16
    berger
    -0.14
    orian
    -0.14
     Degree
    -0.14
    uga
    -0.14
    alan
    -0.14
    ai
    -0.13
    jom
    -0.13
    YO
    -0.13
    leo
    -0.13
    POSITIVE LOGITS
    -âĢIJ
    0.16
     requestOptions
    0.15
    ippers
    0.15
    OA
    0.14
    awner
    0.14
    nave
    0.14
    fuse
    0.14
     Glo
    0.14
    unifu
    0.14
    bourg
    0.13
    Act Density 0.227%

    No Known Activations