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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks alone

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation that signify the completion of thoughts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     escal
    -0.68
     maniac
    -0.68
     displacement
    -0.68
     luxury
    -0.67
     displaced
    -0.65
     shuttle
    -0.65
    ounter
    -0.65
     enrol
    -0.65
     vill
    -0.65
     turnover
    -0.64
    POSITIVE LOGITS
     Anyway
    1.41
    Firstly
    1.36
    Anyway
    1.32
     Firstly
    1.30
     Basically
    1.11
     Suff
    1.10
     suffice
    1.04
     Nonetheless
    1.03
     Nevertheless
    1.02
     Essentially
    1.02
    Act Density 0.656%

    No Known Activations