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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "guilty"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gee
    -0.17
    ãĥ¼ãĥĢ
    -0.16
    roe
    -0.15
    alog
    -0.15
    ollen
    -0.14
    clerosis
    -0.14
    ierz
    -0.14
    alet
    -0.14
    alah
    -0.14
    erek
    -0.14
    POSITIVE LOGITS
    ijkstra
    0.17
     hers
    0.15
     Pine
    0.15
    awai
    0.15
     yours
    0.14
    OURS
    0.14
    å¡ļ
    0.14
    yc
    0.14
     cocci
    0.14
    reetings
    0.13
    Act Density 0.002%

    No Known Activations