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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions to perform certain actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to instructions or actions to take

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.86
    arious
    -0.70
    blooded
    -0.66
    stood
    -0.65
     lasts
    -0.64
    Jud
    -0.64
    leaders
    -0.63
    hearted
    -0.63
     goodwill
    -0.63
    democracy
    -0.63
    POSITIVE LOGITS
     configure
    1.37
     manually
    1.36
     use
    1.35
     specify
    1.35
     modify
    1.29
     utilize
    1.26
     customize
    1.25
     install
    1.25
     choose
    1.22
     omit
    1.20
    Act Density 0.340%

    No Known Activations