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

    Neuronpedia

    INDEX
    Explanations

    phrases related to blog posts and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     CTR
    -0.70
     Dickinson
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.64
     Sergeant
    -0.63
     CoC
    -0.63
     PLA
    -0.63
    yards
    -0.63
    terday
    -0.61
     Arist
    -0.60
    idential
    -0.60
    POSITIVE LOGITS
    ceans
    1.30
    vernight
    1.21
    scill
    1.16
    atmeal
    1.15
    mbudsman
    1.14
    culus
    1.12
    lymp
    1.11
    phthal
    1.03
    mega
    1.03
    zzy
    1.02
    Act Density 0.456%

    No Known Activations