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

    Neuronpedia

    INDEX
    Explanations

    portmanteau words combining "un" and some other word to form a negative meaning

    oai_token-act-pair · gpt-3.5-turbo

    words related to achieving or attainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.65
     recurring
    -0.64
     Hath
    -0.62
     racks
    -0.62
     drinking
    -0.60
     periods
    -0.60
    holders
    -0.59
     ports
    -0.59
    wives
    -0.57
     Binary
    -0.56
    POSITIVE LOGITS
    iev
    1.49
    icz
    1.34
    rov
    1.10
    ideo
    0.94
    nik
    0.94
    ski
    0.93
    rolet
    0.91
    agin
    0.91
    arov
    0.90
    ovsky
    0.89
    Act Density 0.005%

    No Known Activations