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

    Neuronpedia

    INDEX
    Explanations

    words related to political or social contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or issues regarding societal or systemic concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favoured
    -0.90
     mathemat
    -0.81
     leaping
    -0.77
     scram
    -0.77
     swat
    -0.75
    xual
    -0.75
     inactive
    -0.75
     precaution
    -0.75
     honoured
    -0.74
     civilisation
    -0.74
    POSITIVE LOGITS
    ³³³³
    1.44
    ³³³³³³³³
    1.34
    ³³³
    1.32
    âĢ
    1.24
    ³³³³³³³³³³³³³³³³
    1.24
    ³³
    1.18
    Brend
    1.12
    ÙĦ
    1.11
    âĶĢâĶĢâĶĢâĶĢ
    1.10
    Statement
    1.09
    Act Density 0.198%

    No Known Activations