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

    Neuronpedia

    INDEX
    Explanations

    phrases related to character relationships and developments in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tradable
    -0.16
    antino
    -0.15
    stract
    -0.15
    rew
    -0.15
    eriod
    -0.13
    atient
    -0.13
     Hiro
    -0.13
     DropIndex
    -0.13
    avana
    -0.13
     ISO
    -0.13
    POSITIVE LOGITS
    WithType
    0.17
    ergus
    0.15
    boxed
    0.15
    ì½ľ
    0.15
    ennon
    0.14
    411
    0.14
     Denn
    0.14
    èĥ¶
    0.13
    KM
    0.13
    åĤ
    0.13
    Act Density 0.151%

    No Known Activations