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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent individuals or discussions around political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.70
    arching
    -0.68
    amia
    -0.66
    berra
    -0.66
    ationally
    -0.65
    multipl
    -0.62
    along
    -0.59
    ãĤ°
    -0.59
    Also
    -0.58
    é¾įå¥ij士
    -0.58
    POSITIVE LOGITS
     concedes
    1.19
     concede
    1.19
     admit
    1.15
     admits
    1.12
     acknowledges
    1.09
     acknowledge
    1.02
     conceded
    0.90
     acknowledging
    0.86
     admitting
    0.86
     admitted
    0.85
    Act Density 0.137%

    No Known Activations