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

    Neuronpedia

    INDEX
    Explanations

    keywords related to abbreviations or acronyms starting with "AB"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of 'AB' identifiers or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.81
     explan
    -0.73
    perse
    -0.72
    lla
    -0.70
    omore
    -0.68
    bourg
    -0.62
    behind
    -0.61
    arium
    -0.61
    bilt
    -0.61
     Beir
    -0.61
    POSITIVE LOGITS
    stract
    1.13
    STR
    1.10
    RIC
    1.10
    OUT
    1.08
    raham
    1.05
    RAM
    1.04
    USE
    0.97
    ORN
    0.94
    BRE
    0.94
    JECT
    0.94
    Act Density 0.034%

    No Known Activations