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

    Neuronpedia

    INDEX
    Explanations

    instances of meeting or encountering people

    oai_token-act-pair · gpt-3.5-turbo

    references to meeting people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eware
    -0.82
    etheless
    -0.82
    ignt
    -0.74
     cone
    -0.74
    vernment
    -0.73
    wcs
    -0.72
     preventive
    -0.72
     membranes
    -0.71
    cul
    -0.69
     manif
    -0.69
    POSITIVE LOGITS
    amorph
    1.15
    ropolis
    0.91
    Meet
    0.77
    OTOS
    0.75
    yll
    0.74
    lehem
    0.73
    APTER
    0.71
    aunt
    0.70
    ablished
    0.68
    tle
    0.68
    Act Density 0.030%

    No Known Activations