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

    Neuronpedia

    INDEX
    Explanations

    paragraph endings beginning with unusual characters that seem to indicate a formatting error or encoding issue

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.86
     CLR
    -0.70
     shack
    -0.69
    ãĥ¼ãĥĨ
    -0.67
     RAD
    -0.67
     Landing
    -0.65
     lethal
    -0.65
     scattering
    -0.64
     Zup
    -0.64
     Morse
    -0.62
    POSITIVE LOGITS
    £
    1.06
    agree
    0.91
    sure
    0.91
    º
    0.91
    ¤
    0.89
    ¼
    0.88
    ª
    0.87
    know
    0.87
    Ń
    0.87
    ¬
    0.85
    Act Density 0.143%

    No Known Activations