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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to entering or exiting various locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bench
    -0.14
    itia
    -0.14
    orio
    -0.14
     Äijá»ĭnh
    -0.14
    .awt
    -0.14
    ordinal
    -0.14
    /inc
    -0.14
    avern
    -0.14
    ignet
    -0.14
    ãĥ¬ãĤ¹
    -0.13
    POSITIVE LOGITS
    atee
    0.18
    idth
    0.15
    .LoggerFactory
    0.14
    roz
    0.14
    ĵĺ
    0.14
    WD
    0.14
     ENTER
    0.14
    ville
    0.14
    ought
    0.13
    tae
    0.13
    Act Density 0.078%

    No Known Activations