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

    Neuronpedia

    INDEX
    Explanations

    warnings and advisories regarding potential dangers or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igue
    -0.15
    èŃľ
    -0.15
    ien
    -0.14
     ноÑĢмаÑĤив
    -0.14
     Deniz
    -0.14
    è°±
    -0.14
    inho
    -0.14
    agr
    -0.14
    maal
    -0.14
    lab
    -0.13
    POSITIVE LOGITS
     about
    0.25
     Warning
    0.23
    warn
    0.23
     warnings
    0.23
     warning
    0.22
    warnings
    0.22
    .warn
    0.22
     warn
    0.21
     warned
    0.20
     signs
    0.20
    Act Density 0.026%

    No Known Activations