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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement and gratitude related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.16
    acht
    -0.15
     Ley
    -0.15
    ataka
    -0.14
    tain
    -0.14
     Rooney
    -0.14
    eyer
    -0.14
    åŀ
    -0.13
    erval
    -0.13
    .ser
    -0.13
    POSITIVE LOGITS
    otel
    0.15
    å¿
    0.14
    reck
    0.14
    mdp
    0.14
    mnop
    0.14
    anine
    0.14
    amas
    0.14
    bish
    0.14
    XD
    0.14
    AAD
    0.14
    Act Density 0.011%

    No Known Activations