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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to database connections and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _tF
    -0.17
    _tA
    -0.17
    дж
    -0.16
    aub
    -0.16
    (KP
    -0.15
    _tE
    -0.15
     kuru
    -0.14
    éĢĨ
    -0.14
    oya
    -0.14
    _tD
    -0.14
    POSITIVE LOGITS
     fail
    0.43
     Fail
    0.36
    fail
    0.33
    Fail
    0.33
     HA
    0.32
    _fail
    0.30
     fails
    0.27
    .fail
    0.27
     failures
    0.27
     failure
    0.25
    Act Density 0.034%

    No Known Activations