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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interpersonal connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Baths
    -0.17
    ignal
    -0.17
     human
    -0.16
    obar
    -0.15
    ÏĦÏģ
    -0.14
     Humans
    -0.14
    olas
    -0.14
    iston
    -0.14
     humans
    -0.14
    olio
    -0.14
    POSITIVE LOGITS
     universe
    0.28
     spirits
    0.28
     Universe
    0.26
     ghosts
    0.23
     spirit
    0.21
    ghost
    0.21
     cosmos
    0.19
     trees
    0.19
     angels
    0.19
     ghost
    0.19
    Act Density 0.025%

    No Known Activations