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

    Neuronpedia

    INDEX
    Explanations

    actions related to conflict and confrontation

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that imply a significant behavioral or impactful event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.81
    sie
    -0.68
    esa
    -0.65
    bie
    -0.63
    oi
    -0.63
    izza
    -0.62
    cess
    -0.62
    liest
    -0.61
    athom
    -0.61
    ippi
    -0.60
    POSITIVE LOGITS
     accordingly
    1.04
     alike
    0.94
     thereafter
    0.87
     therein
    0.79
     thereof
    0.76
     thereto
    0.74
     consequently
    0.73
     thereby
    0.73
     anew
    0.68
     afterwards
    0.68
    Act Density 0.409%

    No Known Activations