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

    Neuronpedia

    INDEX
    Explanations

    unique characters or symbols like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    numerical or date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dotted
    -0.72
     Hust
    -0.70
    ouver
    -0.69
     resume
    -0.69
     mosqu
    -0.67
    ĸļ
    -0.67
     purs
    -0.66
     yearly
    -0.64
    awaru
    -0.64
     dreaded
    -0.63
    POSITIVE LOGITS
    https
    0.90
    any
    0.84
    http
    0.79
    Link
    0.76
    VAL
    0.75
    Recent
    0.72
    Member
    0.72
    Show
    0.71
    Updated
    0.71
    Premium
    0.71
    Act Density 0.106%

    No Known Activations