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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names as pairs or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals' names or titles in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olutions
    -0.84
    eco
    -0.77
    ipt
    -0.68
    itizens
    -0.67
    izen
    -0.65
     Higher
    -0.64
     metab
    -0.64
     adaptations
    -0.64
     outputs
    -0.63
    pec
    -0.61
    POSITIVE LOGITS
     whom
    1.60
     who
    1.27
    who
    1.24
     whose
    1.14
    whose
    1.13
     Jr
    1.11
     Sr
    0.95
    Jr
    0.88
     although
    0.85
     albeit
    0.81
    Act Density 0.271%

    No Known Activations