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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in the format of 'month, day, year'

    oai_token-act-pair · gpt-3.5-turbo

    numbers and numerical data, particularly those related to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.53
    ĵĺ
    -0.51
     exha
    -0.46
    etheless
    -0.42
     pse
    -0.41
     tremend
    -0.41
     tradem
    -0.40
     mathemat
    -0.40
     newcom
    -0.39
     satell
    -0.39
    POSITIVE LOGITS
     onward
    0.41
    GV
    0.39
    ividual
    0.38
     onwards
    0.37
    tenance
    0.37
    èĢħ
    0.36
    uart
    0.36
    3000
    0.36
    代
    0.36
    083
    0.36
    Act Density 1.617%

    No Known Activations