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

    Neuronpedia

    INDEX
    Explanations

    words related to granting or receiving favors, especially in political or business contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to political favors and favoritism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.79
    borg
    -0.79
    oufl
    -0.73
    anwhile
    -0.73
    prototype
    -0.71
    ways
    -0.68
    bridge
    -0.67
    mberg
    -0.66
    teen
    -0.66
    ı
    -0.66
    POSITIVE LOGITS
    itism
    1.62
    ited
    1.00
    ably
    0.92
    itures
    0.89
     favors
    0.79
    itive
    0.77
    hift
    0.76
    IOR
    0.75
    iture
    0.71
     favoring
    0.70
    Act Density 0.021%

    No Known Activations