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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to groups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities with high influence or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.57
    verted
    -0.56
     Afterwards
    -0.55
    ikers
    -0.54
    Insp
    -0.54
    ãĥ¬
    -0.54
    uted
    -0.53
    ixt
    -0.52
    wordpress
    -0.52
    Wikipedia
    -0.52
    POSITIVE LOGITS
     needs
    1.18
     already
    1.11
     wants
    1.08
     could
    1.08
     knows
    1.06
     might
    1.06
     prefers
    1.03
     intends
    1.02
     may
    1.02
     lacks
    1.01
    Act Density 0.521%

    No Known Activations