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

    Neuronpedia

    INDEX
    Explanations

    elements related to scoring mechanics in a game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    кÑĥл
    -0.19
    ihn
    -0.18
    luv
    -0.16
    çĪ½
    -0.15
    ittest
    -0.15
    pu
    -0.14
     Sı
    -0.14
     saber
    -0.14
     ↵
    -0.13
    kit
    -0.13
    POSITIVE LOGITS
     jack
    0.26
     weight
    0.21
     bowl
    0.21
     Jack
    0.20
     shot
    0.19
     shots
    0.19
     Weight
    0.19
     bowls
    0.19
    Jack
    0.18
    jack
    0.17
    Act Density 0.004%

    No Known Activations