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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    key phrases that indicate issues of high importance or priority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.84
    apons
    -0.76
    onyms
    -0.76
    ampires
    -0.74
    yss
    -0.74
    orks
    -0.74
    icro
    -0.70
    renches
    -0.69
    agate
    -0.68
    odes
    -0.68
    POSITIVE LOGITS
     unto
    0.90
     reliever
    0.82
     pursued
    0.77
     nowadays
    0.71
     breaker
    0.71
    bender
    0.70
    stay
    0.69
     occurrence
    0.69
     fixture
    0.68
     perpetrated
    0.66
    Act Density 0.227%

    No Known Activations