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

    Neuronpedia

    INDEX
    Explanations

    commands or phrases that prompt action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ove
    -0.16
    oola
    -0.16
    rawer
    -0.15
    ufe
    -0.15
    pu
    -0.15
    agues
    -0.14
    idis
    -0.14
    ocale
    -0.14
    ruh
    -0.14
    ADX
    -0.14
    POSITIVE LOGITS
     down
    0.24
     amongst
    0.23
     cracking
    0.20
     busy
    0.20
     active
    0.19
    -to
    0.19
     thee
    0.18
    down
    0.18
     suited
    0.18
     together
    0.18
    Act Density 0.054%

    No Known Activations