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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and scientific investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.83
     Gareth
    -0.66
    ness
    -0.65
    fcntl
    -0.65
    ceph
    -0.64
    }_{(
    -0.63
    Gareth
    -0.63
    ă
    -0.62
     skar
    -0.62
    бав
    -0.61
    POSITIVE LOGITS
     study
    1.46
     studies
    1.45
    STUDY
    1.44
    study
    1.40
     Study
    1.36
    studies
    1.30
    Study
    1.28
     Studied
    1.24
     studie
    1.23
     STUDY
    1.21
    Act Density 0.104%

    No Known Activations