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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating errors or invalid states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zn
    -0.15
    ãģĭãĤı
    -0.15
    abbr
    -0.15
    zioni
    -0.14
    gear
    -0.14
    umer
    -0.14
    ÅĻik
    -0.14
    ikes
    -0.14
    ENTA
    -0.14
    okens
    -0.14
    POSITIVE LOGITS
     Gregg
    0.14
    chie
    0.14
    eneric
    0.13
    ely
    0.13
    StartPosition
    0.13
    -flag
    0.13
    Merit
    0.13
    ï¼³
    0.13
    Ñĩа
    0.13
    çIJ³
    0.13
    Act Density 0.031%

    No Known Activations