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

    Neuronpedia

    INDEX
    Explanations

    mentions of collaborative or cooperative efforts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "work" in various contexts related to collaboration and effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.82
     Seym
    -0.70
    anamo
    -0.67
     Bubble
    -0.66
    ILLE
    -0.66
     Tang
    -0.65
     snap
    -0.64
    iren
    -0.63
    aval
    -0.61
    fal
    -0.60
    POSITIVE LOGITS
     ethic
    1.15
    bench
    1.08
    station
    0.98
    hops
    0.93
    fare
    0.89
    forces
    0.87
    ington
    0.86
    flows
    0.85
    manship
    0.84
    natureconservancy
    0.80
    Act Density 0.083%

    No Known Activations