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

    Neuronpedia

    INDEX
    Explanations

    phrases that express awareness or the presence of something significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITTE
    -0.19
    mpr
    -0.15
    маз
    -0.14
    iates
    -0.14
    ãĤ·ãĤ¢
    -0.14
    etta
    -0.14
    issing
    -0.14
    nar
    -0.14
    GuidId
    -0.13
     Things
    -0.13
    POSITIVE LOGITS
     mention
    0.32
     mentions
    0.29
     references
    0.24
    mentions
    0.24
     Mention
    0.23
     hint
    0.22
     discussion
    0.22
     announcement
    0.21
    mention
    0.21
     hints
    0.21
    Act Density 0.027%

    No Known Activations