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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the character 'Z' and references to specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cers
    -0.69
     minded
    -0.65
    sers
    -0.64
    croft
    -0.61
     thous
    -0.61
     Cheong
    -0.60
     Staples
    -0.60
     unpre
    -0.59
    escent
    -0.59
    pole
    -0.58
    POSITIVE LOGITS
    ombie
    1.51
    ombies
    1.49
    ERO
    1.32
    odiac
    1.17
    ebra
    1.12
    imbabwe
    1.12
    ooming
    1.05
    oom
    1.04
    eus
    1.02
    hao
    1.02
    Act Density 0.034%

    No Known Activations