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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or escape from one location or state to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    exiting from a location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.56
    Билгалдахарш
    -0.55
    뀜
    -0.54
     kasarigan
    -0.53
     ſtand
    -0.53
    ConstraintMaker
    -0.52
    elemField
    -0.51
     Bioaccumulative
    -0.49
     iſt
    -0.48
    BeNil
    -0.47
    POSITIVE LOGITS
    enumi
    0.59
    Exiting
    0.54
     exiting
    0.53
     khỏi
    0.50
    走出
    0.50
    enumii
    0.48
     quitté
    0.46
     the
    0.46
     exit
    0.45
     Exit
    0.44
    Act Density 0.082%

    No Known Activations