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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activity

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or end-of-sentence markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uph
    -0.87
     favor
    -0.80
    aez
    -0.72
    lihood
    -0.71
    Newsletter
    -0.71
    ennial
    -0.71
     someday
    -0.69
     favors
    -0.68
    aterasu
    -0.66
    adra
    -0.65
    POSITIVE LOGITS
    Writing
    0.82
    ONDON
    0.77
    Ireland
    0.74
     DUP
    0.72
    Scotland
    0.71
     Universities
    0.71
    Britain
    0.70
     Ulster
    0.69
     paed
    0.68
     MPs
    0.67
    Act Density 0.321%

    No Known Activations