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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence of organizations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caller
    -0.67
    iddler
    -0.64
     Checking
    -0.63
    Mech
    -0.63
    isher
    -0.60
     additional
    -0.59
     Landing
    -0.58
     Metatron
    -0.58
     docking
    -0.57
     clearing
    -0.56
    POSITIVE LOGITS
     celebrates
    0.94
     resembles
    0.91
     thri
    0.89
     wors
    0.88
     lacks
    0.88
     embodies
    0.85
     spans
    0.83
     loves
    0.82
     encompasses
    0.82
     horr
    0.81
    Act Density 0.167%

    No Known Activations