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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases related to uncertainty or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    conditional and relational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]}
    -0.57
    /?
    -0.52
     âĢİ
    -0.51
     Bots
    -0.51
    "}
    -0.49
     assailants
    -0.49
     sovere
    -0.49
     recount
    -0.48
     Amen
    -0.48
     Rampage
    -0.48
    POSITIVE LOGITS
    neutral
    0.64
    ivating
    0.63
    ongevity
    0.62
    apest
    0.62
    uay
    0.61
    wikipedia
    0.61
    onom
    0.60
    ivation
    0.60
    arming
    0.60
    pton
    0.60
    Act Density 2.142%

    No Known Activations