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

    Neuronpedia

    INDEX
    Explanations

    references to digging or burrowing activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to rowing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.80
    arta
    -0.77
     Mahjong
    -0.75
    ++++++++
    -0.71
    URI
    -0.70
     Lumpur
    -0.69
    ennis
    -0.69
    orgetown
    -0.69
     lou
    -0.69
     Franch
    -0.68
    POSITIVE LOGITS
    geon
    0.84
    blers
    0.72
    vet
    0.71
    rowing
    0.69
    things
    0.69
    MpServer
    0.69
    iot
    0.69
    bow
    0.68
    geons
    0.68
    pid
    0.67
    Act Density 0.001%

    No Known Activations