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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.67
     Larsson
    -0.65
    dhist
    -0.61
    qxd
    -0.60
     Borja
    -0.60
     Tos
    -0.59
     Pfalz
    -0.59
    ábbi
    -0.58
     Alain
    -0.57
    DotNetBar
    -0.57
    POSITIVE LOGITS
    know
    1.44
     know
    1.42
     Know
    1.40
    Know
    1.39
    KNOW
    1.35
     knows
    1.34
     KNOW
    1.30
     Knows
    1.22
    knows
    1.21
    knew
    1.18
    Act Density 0.132%

    No Known Activations