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

    Neuronpedia

    INDEX
    Explanations

    mentions of entities being supported or funded by an external source

    oai_token-act-pair · gpt-3.5-turbo

    terms related to state-supported or government-backed initiatives and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjustment
    -0.64
     experience
    -0.63
     inflic
    -0.62
     sample
    -0.62
     dial
    -0.61
     empt
    -0.61
     som
    -0.61
     duration
    -0.60
     per
    -0.59
     Mystic
    -0.59
    POSITIVE LOGITS
    backed
    3.88
     backed
    1.72
    supported
    1.67
    sponsored
    1.59
    back
    1.49
    funded
    1.41
    backs
    1.28
    aligned
    1.26
    led
    1.21
    linked
    1.19
    Act Density 0.012%

    No Known Activations