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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product features and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     taboo
    -0.75
     millennium
    -0.75
    orno
    -0.74
     unsustainable
    -0.73
     unstoppable
    -0.70
     acute
    -0.70
     feared
    -0.69
     slump
    -0.68
     sustainable
    -0.68
     gloom
    -0.66
    POSITIVE LOGITS
     Additionally
    1.53
     Alternatively
    1.52
     Interestingly
    1.41
     Basically
    1.36
     However
    1.32
     Presumably
    1.31
     Essentially
    1.31
     Lastly
    1.30
     Unfortunately
    1.30
     Also
    1.30
    Act Density 0.328%

    No Known Activations