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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating performance metrics or statistics in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ço
    -0.15
     rains
    -0.15
     batting
    -0.14
    飯
    -0.14
     frags
    -0.14
    VA
    -0.14
    SGlobal
    -0.14
     bat
    -0.14
    VP
    -0.14
    ustral
    -0.13
    POSITIVE LOGITS
     Hockey
    0.28
     Frozen
    0.26
    Frozen
    0.26
     hockey
    0.22
     puck
    0.21
     frozen
    0.21
     goalt
    0.20
     ice
    0.20
     Hob
    0.19
     skate
    0.18
    Act Density 0.017%

    No Known Activations