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

    Neuronpedia

    INDEX
    Explanations

    actions related to movement and transitions between spaces or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dsp
    -0.16
     corners
    -0.15
     Corner
    -0.15
     ded
    -0.14
    unsch
    -0.14
    icial
    -0.14
    usercontent
    -0.13
    ÛĮات
    -0.13
    Spaces
    -0.13
    eos
    -0.13
    POSITIVE LOGITS
     door
    0.81
     doors
    0.73
     Door
    0.65
    door
    0.63
    Door
    0.62
    éŨ
    0.62
     Doors
    0.59
    -door
    0.59
    doors
    0.56
     двеÑĢ
    0.56
    Act Density 0.178%

    No Known Activations