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

    Neuronpedia

    INDEX
    Explanations

    metaphors and comparisons related to comfort and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jom
    -0.15
     getchar
    -0.14
    ogne
    -0.14
    LIK
    -0.14
    Äħd
    -0.14
     assignable
    -0.14
    ès
    -0.13
    emmel
    -0.13
     Lon
    -0.13
    jun
    -0.13
    POSITIVE LOGITS
     бÑĥдÑĤо
    0.18
    unsafe
    0.15
    rels
    0.14
    ÃĹ↵↵
    0.14
    γοÏģ
    0.14
     Ih
    0.14
     certainty
    0.14
    gne
    0.13
    rina
    0.13
    609
    0.13
    Act Density 0.138%

    No Known Activations