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

    Neuronpedia

    INDEX
    Explanations

    people being appointed or selected for positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts, often to indicate designation or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.79
    raq
    -0.77
    leness
    -0.71
    auri
    -0.69
    ubb
    -0.68
    ieval
    -0.67
    ecd
    -0.67
     ACTIONS
    -0.65
    length
    -0.64
    alloc
    -0.64
    POSITIVE LOGITS
    pired
    1.03
     opposed
    1.03
     well
    1.01
    pires
    0.95
     soon
    0.92
    ynchron
    0.92
     part
    0.88
     follows
    0.85
    part
    0.83
    piring
    0.78
    Act Density 0.203%

    No Known Activations