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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict, competition, and power struggles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating competition or conflict over resources or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.81
    ilst
    -0.76
    ighed
    -0.76
    cano
    -0.71
    ħĭ
    -0.69
    orry
    -0.69
    quist
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
     Nope
    -0.67
    ²¾
    -0.67
    POSITIVE LOGITS
     supremacy
    1.35
     dominance
    1.27
     scraps
    1.15
     survival
    1.14
     control
    1.05
     scarce
    1.01
     custody
    0.97
     position
    0.97
     hegemony
    0.97
     turf
    0.94
    Act Density 0.138%

    No Known Activations