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

    Neuronpedia

    INDEX
    Explanations

    intensity descriptors related to competition or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.92
    uration
    -0.82
    urated
    -0.79
    ablish
    -0.73
    isphere
    -0.71
     Peb
    -0.70
    代
    -0.69
    abad
    -0.68
    ammy
    -0.68
    roma
    -0.68
    POSITIVE LOGITS
     competitor
    0.93
    ly
    0.91
     competition
    0.91
     battle
    0.85
     critic
    0.84
     fierce
    0.83
     competitive
    0.82
     battles
    0.82
    tails
    0.80
     antic
    0.80
    Act Density 0.015%

    No Known Activations