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

    Neuronpedia

    INDEX
    Explanations

    terms associated with medical or health-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pler
    -0.17
    BOTTOM
    -0.16
    _frontend
    -0.15
    opper
    -0.15
     BOTTOM
    -0.15
    enor
    -0.14
    oren
    -0.14
     Separator
    -0.14
    adow
    -0.14
    orks
    -0.14
    POSITIVE LOGITS
     beyond
    0.50
     Beyond
    0.42
    Beyond
    0.38
     early
    0.32
     throughout
    0.29
     into
    0.27
    early
    0.27
    eyond
    0.26
     Early
    0.23
     Throughout
    0.22
    Act Density 0.075%

    No Known Activations