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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe spatial relationships and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Depth
    -0.17
    eneral
    -0.15
    inium
    -0.15
    voy
    -0.14
    ighth
    -0.14
    .connection
    -0.14
    ħn
    -0.14
    uctions
    -0.14
    acades
    -0.14
    depth
    -0.13
    POSITIVE LOGITS
     front
    0.39
    front
    0.34
     FRONT
    0.30
    -front
    0.29
    _front
    0.24
    Front
    0.23
     fron
    0.23
    .front
    0.21
     fronts
    0.21
     Front
    0.21
    Act Density 0.184%

    No Known Activations