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

    Neuronpedia

    INDEX
    Explanations

    couples or pairs of related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.83
     princ
    -0.80
     willpower
    -0.69
     handshake
    -0.68
     bluff
    -0.68
     notor
    -0.67
     charter
    -0.66
     anecd
    -0.65
     hemisphere
    -0.65
     stret
    -0.64
    POSITIVE LOGITS
    âĢ
    1.70
     âĢ
    1.33
    ãĢ
    1.32
    ·
    1.28
    âĦ¢
    1.24
    âĺ
    1.24
    âĢł
    1.22
    \.
    1.20
    âĶ
    1.19
    ®
    1.18
    Act Density 0.511%

    No Known Activations