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

    Neuronpedia

    INDEX
    Explanations

    slashes (/)

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or forward slashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.78
     explan
    -0.77
     defe
    -0.76
     misunder
    -0.76
    acters
    -0.75
     Beir
    -0.75
    uration
    -0.72
    hower
    -0.72
    sembly
    -0.72
    ulkan
    -0.70
    POSITIVE LOGITS
    ËĪ
    1.44
    usr
    0.97
    etc
    0.88
     Via
    0.86
    Film
    0.81
    home
    0.79
    join
    0.77
    pol
    0.76
    ********************************
    0.76
    wcsstore
    0.75
    Act Density 0.014%

    No Known Activations