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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to handling or using a particular item or product

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vou
    -0.68
    roid
    -0.65
     forwarded
    -0.64
     Gilmore
    -0.63
    amac
    -0.60
    redd
    -0.58
    estern
    -0.58
    naissance
    -0.57
    usc
    -0.57
    ements
    -0.57
    POSITIVE LOGITS
    Pause
    0.66
     Default
    0.65
    Minimum
    0.62
     Parameters
    0.62
    Else
    0.60
    Notable
    0.59
    Example
    0.58
     Example
    0.57
     Recommended
    0.57
     Requirements
    0.57
    Act Density 0.223%

    No Known Activations