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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions and processes

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arel
    -0.74
    esa
    -0.68
    adelphia
    -0.67
     ][
    -0.66
    aina
    -0.66
    sie
    -0.64
    arger
    -0.64
    cess
    -0.63
    ocaust
    -0.63
    degree
    -0.61
    POSITIVE LOGITS
     accordingly
    1.09
     thereafter
    0.82
     alike
    0.79
     himself
    0.78
     herself
    0.77
     thereto
    0.72
     afterward
    0.70
     afterwards
    0.70
     therein
    0.68
     consequently
    0.66
    Act Density 0.347%

    No Known Activations