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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to audience engagement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halb
    -0.16
    chet
    -0.16
    enberg
    -0.14
    eyin
    -0.14
    CHASE
    -0.14
    .story
    -0.14
    ewan
    -0.14
    enda
    -0.14
    /original
    -0.13
    ourcem
    -0.13
    POSITIVE LOGITS
    ili
    0.15
    561
    0.15
     Roth
    0.14
    461
    0.14
    BJ
    0.14
     Rue
    0.14
    ermen
    0.14
     iParam
    0.14
    æĪ
    0.13
    _capacity
    0.13
    Act Density 0.528%

    No Known Activations