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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cause and effect or instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grip
    -0.73
    rament
    -0.72
     purse
    -0.69
     sustained
    -0.69
     spoiled
    -0.68
     lately
    -0.68
     bush
    -0.67
     pard
    -0.67
     lap
    -0.66
     aven
    -0.66
    POSITIVE LOGITS
     Each
    1.37
     Depending
    1.37
     Additionally
    1.32
     Ideally
    1.27
     Alternatively
    1.25
     Typically
    1.25
     Examples
    1.24
     Conversely
    1.23
     Usually
    1.20
     Essentially
    1.19
    Act Density 0.695%

    No Known Activations