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

    Neuronpedia

    INDEX
    Explanations

    words related to exits or leaving in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exit" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PROV
    -0.68
    uth
    -0.61
     archae
    -0.60
     BAS
    -0.60
    REC
    -0.60
     photographer
    -0.60
    wark
    -0.59
     Army
    -0.58
    oust
    -0.58
    âĻ¥
    -0.58
    POSITIVE LOGITS
    Exit
    3.31
     exited
    2.82
     exits
    2.53
    exit
    2.34
     exiting
    2.33
     exit
    2.24
     Exit
    2.03
    xit
    1.69
     ejected
    1.44
     eject
    1.35
    Act Density 0.022%

    No Known Activations