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

    Neuronpedia

    INDEX
    Explanations

    the symbol 'Ċ' at various locations within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aroo
    -0.74
    oise
    -0.71
    lete
    -0.67
    letes
    -0.65
     Double
    -0.64
    chester
    -0.64
    izabeth
    -0.64
    icter
    -0.63
    ichick
    -0.62
    creen
    -0.62
    POSITIVE LOGITS
    ccording
    1.02
    Britain
    0.82
    India
    0.78
    Germany
    0.77
    European
    0.76
    Reuters
    0.76
    Tok
    0.75
    Ukraine
    0.75
    IAL
    0.73
    AFP
    0.70
    Act Density 0.122%

    No Known Activations