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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases related to embedding and insertion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     filetype
    -0.17
    527
    -0.14
    227
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    rette
    -0.14
     successes
    -0.14
    eba
    -0.13
     Pb
    -0.13
    orca
    -0.13
     Fur
    -0.13
    POSITIVE LOGITS
    iras
    0.20
    ναν
    0.16
     Gord
    0.15
    oll
    0.15
     diseñador
    0.15
    /Public
    0.14
    asley
    0.14
    munition
    0.14
    roe
    0.14
    ollen
    0.14
    Act Density 0.390%

    No Known Activations