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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being in the spotlight or gaining attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ponder
    -0.18
    usto
    -0.16
    aleb
    -0.16
    oplan
    -0.15
    oire
    -0.14
    afa
    -0.14
    #
    -0.14
     Gaut
    -0.14
    olec
    -0.14
    gone
    -0.14
    POSITIVE LOGITS
     attention
    0.22
    attention
    0.18
     Attention
    0.17
     tro
    0.15
     Shed
    0.14
    etro
    0.14
    spot
    0.14
     recip
    0.14
    suffix
    0.14
    rou
    0.14
    Act Density 0.050%

    No Known Activations