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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for mentions of something being under public scrutiny or receiving attention from the public or media

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spotlight" and its related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.82
    ihad
    -0.72
    meal
    -0.71
    ajor
    -0.69
    llular
    -0.66
    lements
    -0.66
    ties
    -0.66
    cod
    -0.65
    THER
    -0.64
    fortune
    -0.63
    POSITIVE LOGITS
     shone
    1.07
    elight
    1.07
     spotlight
    1.04
     shines
    0.90
     shine
    0.84
     Spotlight
    0.79
     glare
    0.76
     shining
    0.74
     showc
    0.72
    wcs
    0.71
    Act Density 0.012%

    No Known Activations