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

    Neuronpedia

    INDEX
    Explanations

    words relating to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    instances of conflict or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.93
    employment
    -0.84
    mental
    -0.82
    vation
    -0.81
    iatric
    -0.72
    ager
    -0.70
    enfranch
    -0.68
    ãģĹ
    -0.68
    intestinal
    -0.67
    secut
    -0.67
    POSITIVE LOGITS
    halla
    1.10
     roy
    0.81
    lag
    0.77
     between
    0.76
     Qiao
    0.70
    SHIP
    0.70
     BET
    0.69
     Amon
    0.69
    FIELD
    0.68
     pits
    0.68
    Act Density 0.026%

    No Known Activations