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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clus
    -0.15
    ory
    -0.15
     Fut
    -0.14
    ht
    -0.14
    çĵ
    -0.14
     Mash
    -0.14
    iedo
    -0.13
    enco
    -0.13
    lete
    -0.13
    ffc
    -0.13
    POSITIVE LOGITS
     unsur
    0.16
    olta
    0.16
    µ¬
    0.16
    KeyType
    0.15
    stor
    0.15
     exp
    0.15
    reater
    0.14
    entin
    0.14
    ogle
    0.14
     Pager
    0.14
    Act Density 0.083%

    No Known Activations