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

    Neuronpedia

    INDEX
    Explanations

    phrases related to joy and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iston
    -0.15
    OOM
    -0.14
    λογ
    -0.14
    _timezone
    -0.14
     jud
    -0.14
    berger
    -0.14
    190
    -0.13
     aw
    -0.13
     GetType
    -0.13
    orea
    -0.13
    POSITIVE LOGITS
    fully
    0.27
    FUL
    0.25
    fulness
    0.23
    FULL
    0.23
    ful
    0.22
    full
    0.21
    ride
    0.20
    ous
    0.18
    ably
    0.17
    odel
    0.17
    Act Density 0.027%

    No Known Activations