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

    Neuronpedia

    INDEX
    Explanations

    mentions related to opinions or judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructions that include the word "of" repeatedly, indicating possession or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endant
    -0.78
    antine
    -0.73
    ower
    -0.69
    Fax
    -0.68
    igent
    -0.68
    auri
    -0.66
    amsung
    -0.66
    auld
    -0.66
    fters
    -0.65
    ocene
    -0.64
    POSITIVE LOGITS
     course
    0.71
     glory
    0.70
     counterparts
    0.69
     mates
    0.67
     theirs
    0.65
     selves
    0.64
    ãģĦ
    0.64
     acquisitions
    0.63
     hers
    0.63
     namesake
    0.62
    Act Density 0.127%

    No Known Activations