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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce subsequent discussions or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oris
    -0.78
    vier
    -0.75
    sav
    -0.74
    contract
    -0.69
    cos
    -0.68
    imon
    -0.67
    ile
    -0.66
    estones
    -0.66
    nor
    -0.66
    orate
    -0.65
    POSITIVE LOGITS
     raining
    0.76
     roaring
    0.68
     undone
    0.67
     flooding
    0.66
     pouring
    0.66
     closer
    0.64
     tro
    0.61
     comparing
    0.61
     tempting
    0.59
     toget
    0.59
    Act Density 0.036%

    No Known Activations