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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pan
    -0.71
    ierre
    -0.67
    ichick
    -0.63
    retch
    -0.62
    fuck
    -0.60
    ijn
    -0.60
    oother
    -0.58
    razil
    -0.57
    urrection
    -0.57
    clerosis
    -0.57
    POSITIVE LOGITS
     by
    1.12
    dden
    0.83
     BY
    0.78
    ãĥ¼ãĥĨ
    0.78
     therein
    0.77
    ħĭ
    0.73
     jointly
    0.73
     during
    0.70
     upon
    0.69
    terness
    0.69
    Act Density 0.295%

    No Known Activations