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

    Neuronpedia

    INDEX
    Explanations

    words related to dispersion and spreading

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to scientific processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.57
     Citiz
    -0.54
     Hunt
    -0.53
     redes
    -0.50
    querque
    -0.50
     Hobby
    -0.50
     Aging
    -0.49
     Jobs
    -0.48
     Guer
    -0.47
     Lives
    -0.47
    POSITIVE LOGITS
    aneously
    0.66
    ysis
    0.63
    lihood
    0.63
    phrine
    0.62
     thereof
    0.58
    imum
    0.56
    xual
    0.55
    phal
    0.55
    actic
    0.54
    berries
    0.54
    Act Density 0.337%

    No Known Activations