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

    Neuronpedia

    INDEX
    Explanations

    programming-related instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating conditions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.95
    iewicz
    -0.83
    beat
    -0.80
    heny
    -0.74
    é¾
    -0.73
    owsky
    -0.73
    buster
    -0.72
    pour
    -0.71
    busters
    -0.70
    jad
    -0.70
    POSITIVE LOGITS
     simplicity
    1.22
     convenience
    1.15
     each
    1.15
     storing
    1.14
     clarity
    1.10
     debugging
    1.08
     purposes
    1.07
     accessing
    1.05
     example
    1.05
    bidden
    1.04
    Act Density 0.143%

    No Known Activations