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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "particularly."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing importance or focus on specific aspects within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.74
    orts
    -0.72
    lee
    -0.72
    IDES
    -0.70
    avan
    -0.69
    lied
    -0.69
    iry
    -0.67
    iny
    -0.67
    hou
    -0.66
    ift
    -0.66
    POSITIVE LOGITS
     rewarding
    0.71
     evidenced
    0.69
     advantageous
    0.67
     associ
    0.67
     susceptible
    0.66
    accompanied
    0.65
     considering
    0.64
     dictated
    0.64
     insofar
    0.64
     egregious
    0.63
    Act Density 0.031%

    No Known Activations