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

    Neuronpedia

    INDEX
    Explanations

    terms related to entertainment and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neglect
    -0.16
    uesta
    -0.15
     when
    -0.15
     cre
    -0.15
     fo
    -0.15
    umont
    -0.15
     e
    -0.15
    ay
    -0.14
    amar
    -0.14
    adox
    -0.14
    POSITIVE LOGITS
    SKI
    0.17
    ityEngine
    0.15
    gang
    0.15
    lingen
    0.15
    empo
    0.15
    okus
    0.15
    ÙĤÙģ
    0.15
    endi
    0.15
    æľŃ
    0.15
    icity
    0.14
    Act Density 0.046%

    No Known Activations