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

    Neuronpedia

    INDEX
    Explanations

    verbs related to commanding or requesting actions

    oai_token-act-pair · gpt-3.5-turbo

    actions or statements made by individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arel
    -0.70
    adelphia
    -0.70
    ortium
    -0.69
    sie
    -0.67
    esa
    -0.66
     ][
    -0.66
    cess
    -0.65
    neys
    -0.63
    ocaust
    -0.63
    ija
    -0.61
    POSITIVE LOGITS
     accordingly
    1.05
     alike
    0.89
     thereafter
    0.89
     consequently
    0.78
     thereof
    0.75
     therein
    0.73
     thereto
    0.73
     thereby
    0.70
     afterwards
    0.70
     afterward
    0.69
    Act Density 0.333%

    No Known Activations