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

    Neuronpedia

    INDEX
    Explanations

    terms associated with closing or ending actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hagan
    -0.35
    SizeMode
    -0.35
    ↹
    -0.33
    PSA
    -0.32
     pre
    -0.31
     Discovery
    -0.31
     Rukh
    -0.31
    tituts
    -0.31
    Discovery
    -0.30
    ayakan
    -0.30
    POSITIVE LOGITS
    fromnode
    0.63
     exited
    0.61
     Exit
    0.58
    SharedDtor
    0.58
     exit
    0.58
    istoitu
    0.57
    uttosto
    0.57
    MemoryWarning
    0.56
    closeConnection
    0.55
    MethodManager
    0.54
    Act Density 0.846%

    No Known Activations