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

    Neuronpedia

    INDEX
    Explanations

    actions related to leaving or exiting a place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nonatomic
    -0.58
     déclar
    -0.55
    posium
    -0.51
    FontOfSize
    -0.51
    DataURL
    -0.50
     ciber
    -0.50
     estime
    -0.50
    __*/
    -0.48
    tosh
    -0.48
    IONA
    -0.47
    POSITIVE LOGITS
     exits
    1.33
     exit
    1.30
     exited
    1.17
     Exit
    1.15
    exit
    1.10
     exiting
    1.08
    Exit
    1.02
    EXIT
    1.00
    Exiting
    0.97
     EXIT
    0.92
    Act Density 0.223%

    No Known Activations