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

    Neuronpedia

    INDEX
    Explanations

    references to television show ratings and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Serif
    -0.16
    iju
    -0.15
     âĶľ
    -0.15
    XHR
    -0.15
    jÃŃm
    -0.14
    еÐ
    -0.14
    834
    -0.14
    emoc
    -0.14
    reu
    -0.14
     Bir
    -0.14
    POSITIVE LOGITS
    奶
    0.13
    LETTE
    0.13
     spin
    0.13
    çĶľ
    0.13
    ork
    0.13
     Karn
    0.13
     instead
    0.13
     L
    0.13
    oucher
    0.13
    lettes
    0.13
    Act Density 0.275%

    No Known Activations