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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures relevant to narrative style and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oth
    -0.17
    iling
    -0.16
    erchant
    -0.16
    zas
    -0.15
    utsch
    -0.15
    apture
    -0.15
    .googlecode
    -0.15
    bsites
    -0.14
    rael
    -0.14
    olf
    -0.14
    POSITIVE LOGITS
    autop
    0.15
    Pull
    0.15
    éļ
    0.14
    ÙĬÙĤ
    0.14
     active
    0.14
    (Constructor
    0.13
    åIJĪæł¼
    0.13
    _PULL
    0.13
    CONDS
    0.13
     Dustin
    0.13
    Act Density 0.018%

    No Known Activations