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

    Neuronpedia

    INDEX
    Explanations

    phrases related to entering or exiting through doors or gates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.16
    inium
    -0.16
    dsp
    -0.15
    gom
    -0.15
    dued
    -0.15
    缤
    -0.14
    icial
    -0.14
     Platz
    -0.14
    asting
    -0.14
    agers
    -0.14
    POSITIVE LOGITS
     door
    0.85
     doors
    0.78
     Door
    0.68
    éŨ
    0.67
    door
    0.67
    Door
    0.65
    -door
    0.63
     Doors
    0.63
    doors
    0.60
    éĸĢ
    0.59
    Act Density 0.210%

    No Known Activations