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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and appreciation in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     phẩm
    -0.15
    emain
    -0.14
    aca
    -0.14
    ignal
    -0.14
    ITTER
    -0.14
    .Batch
    -0.14
    _literals
    -0.14
    Batch
    -0.14
    åĶ
    -0.14
    itter
    -0.13
    POSITIVE LOGITS
    :animated
    0.16
    INET
    0.15
    quo
    0.14
    enet
    0.14
     Fat
    0.14
    ελ
    0.14
    asers
    0.14
    .shiro
    0.13
    emplates
    0.13
     adher
    0.13
    Act Density 0.073%

    No Known Activations