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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve sending or directing someone or something to a specific location or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okrat
    -0.16
    wards
    -0.15
    ewed
    -0.14
    oga
    -0.14
     eg
    -0.14
    ibi
    -0.14
    ews
    -0.14
    uing
    -0.14
    ————————————————
    -0.14
    _sidebar
    -0.13
    POSITIVE LOGITS
     packing
    0.35
     Packing
    0.28
    packing
    0.22
     home
    0.20
     forth
    0.20
     sent
    0.19
     tum
    0.19
    PACK
    0.18
     into
    0.18
     Spir
    0.17
    Act Density 0.031%

    No Known Activations