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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commentary and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelProperty
    -0.16
    tron
    -0.16
    tec
    -0.14
    lug
    -0.14
    icker
    -0.14
     UIEdgeInsets
    -0.14
    éal
    -0.13
    Frameworks
    -0.13
    oret
    -0.13
    ws
    -0.13
    POSITIVE LOGITS
     naturally
    0.24
     Naturally
    0.19
     decided
    0.18
    ứng
    0.18
    اة
    0.16
     couldn
    0.16
     cash
    0.15
     wouldn
    0.15
     wants
    0.15
     logical
    0.15
    Act Density 0.090%

    No Known Activations