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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to medical interventions and targeting in health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aira
    -0.15
     Tune
    -0.14
     Toll
    -0.14
    aga
    -0.14
     Trom
    -0.14
    aye
    -0.14
     Tenant
    -0.13
    orton
    -0.13
    tif
    -0.13
    ala
    -0.13
    POSITIVE LOGITS
     target
    1.30
    target
    1.15
     targets
    1.13
     Target
    1.10
    Target
    1.05
    -target
    1.02
    _target
    1.00
     Targets
    0.98
     TARGET
    0.96
    .target
    0.95
    Act Density 0.211%

    No Known Activations