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

    Neuronpedia

    INDEX
    Explanations

    references to sports team names and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.76
    principalTable
    -0.57
    ')))
    -0.56
     TestBed
    -0.54
     незавершена
    -0.54
    jspx
    -0.54
    DataMember
    -0.53
    ))));
    -0.53
     lenker
    -0.52
     réessayer
    -0.52
    POSITIVE LOGITS
     undefeated
    0.84
     unbeaten
    0.83
     wins
    0.78
     victories
    0.74
    wins
    0.73
     defeats
    0.71
     losses
    0.70
     win
    0.69
    win
    0.69
     winning
    0.64
    Act Density 0.135%

    No Known Activations