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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or knowledge of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Strap
    -0.15
     Barbar
    -0.15
    onto
    -0.15
    strap
    -0.14
    .semantic
    -0.14
    .relative
    -0.14
     strap
    -0.14
    gz
    -0.14
     Contest
    -0.13
    )|(
    -0.13
    POSITIVE LOGITS
    $MESS
    0.15
    apg
    0.14
    alse
    0.14
    оналÑĮ
    0.14
    iah
    0.14
    ãĥ¼ãĥĬ
    0.14
     boa
    0.14
    \Php
    0.14
    оÑģÑĮ
    0.14
     Tier
    0.14
    Act Density 0.143%

    No Known Activations