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

    Neuronpedia

    INDEX
    Explanations

    references to collective terms for people, indicating a focus on community or group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crot
    -0.93
    icorn
    -0.82
    RunWith
    -0.79
    slidesPer
    -0.78
     trails
    -0.76
    kids
    -0.75
    }_{+
    -0.75
     BoxFit
    -0.74
     dinos
    -0.74
    повід
    -0.74
    POSITIVE LOGITS
    Everybody
    1.10
    everybody
    1.07
     Everybody
    1.05
     Anybody
    0.96
    theless
    0.96
     everybody
    0.94
    somebody
    0.94
     anybody
    0.90
    Anybody
    0.89
    parsedMessage
    0.88
    Act Density 0.072%

    No Known Activations