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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "scored" and variations related to scoring in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.76
    tact
    -0.51
    仕方
    -0.50
    ochet
    -0.48
    urge
    -0.48
    GEBURTSDATUM
    -0.47
     thank
    -0.46
    mendation
    -0.46
    Przyp
    -0.46
     scape
    -0.46
    POSITIVE LOGITS
     scoring
    0.85
     scored
    0.79
     Scoring
    0.76
    Scoring
    0.71
    scoring
    0.68
    UnsafeEnabled
    0.68
    scored
    0.57
     scorers
    0.54
     importantly
    0.50
     numberOfRows
    0.45
    Act Density 0.086%

    No Known Activations