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

    Neuronpedia

    INDEX
    Explanations

    actions related to scoring and winning in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ats
    -0.18
    atsu
    -0.17
    andom
    -0.16
    _stuff
    -0.15
    ATS
    -0.15
    standen
    -0.15
     canc
    -0.14
    .scalablytyped
    -0.14
    erti
    -0.14
    anta
    -0.14
    POSITIVE LOGITS
     maximum
    0.25
     hon
    0.25
     brag
    0.24
     precious
    0.23
     valuable
    0.22
     silver
    0.21
     pole
    0.21
     points
    0.20
     Maximum
    0.20
     pride
    0.19
    Act Density 0.052%

    No Known Activations