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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yen
    -0.17
    úb
    -0.16
    essler
    -0.15
    agra
    -0.15
    uars
    -0.15
    letes
    -0.14
    aturas
    -0.14
     Blackburn
    -0.14
    ahr
    -0.14
    (SIG
    -0.14
    POSITIVE LOGITS
    orate
    0.37
    antly
    0.32
    ations
    0.24
    oration
    0.23
    entially
    0.19
    ativas
    0.18
    ant
    0.18
    nation
    0.17
    ably
    0.17
    à¸ģารà¸ĵ
    0.16
    Act Density 0.044%

    No Known Activations