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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and plans

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.84
     spor
    -0.73
    ividual
    -0.73
     frequently
    -0.71
     occasional
    -0.70
     leveled
    -0.69
    icrobial
    -0.69
     prosec
    -0.69
     transact
    -0.68
     occasionally
    -0.68
    POSITIVE LOGITS
     Luckily
    1.42
     Instead
    1.34
     Turns
    1.32
     Fortunately
    1.32
     Accordingly
    1.31
     Unfortunately
    1.31
     So
    1.24
     Thankfully
    1.21
    Luckily
    1.21
     Naturally
    1.17
    Act Density 0.465%

    No Known Activations