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

    Neuronpedia

    INDEX
    Explanations

    references to hotels and accommodations during travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azes
    -0.17
     species
    -0.14
     Reco
    -0.14
     Species
    -0.13
    star
    -0.13
    rides
    -0.13
    οÏħÏĤ
    -0.13
    azz
    -0.13
     tut
    -0.13
    Shortcut
    -0.13
    POSITIVE LOGITS
    uru
    0.16
    ernals
    0.15
    uisse
    0.15
    uraa
    0.15
    cci
    0.14
    ngine
    0.14
    eyh
    0.14
    588
    0.14
    583
    0.14
     sensit
    0.14
    Act Density 0.010%

    No Known Activations