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

    Neuronpedia

    INDEX
    Explanations

    references to mobile applications

    oai_token-act-pair · gpt-3.5-turbo

    references to mobile applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tract
    -0.67
     Maul
    -0.62
     Deity
    -0.62
    bilt
    -0.61
     cigars
    -0.58
    nces
    -0.57
    anson
    -0.57
     Rhodes
    -0.56
     Clown
    -0.55
     speeches
    -0.55
    POSITIVE LOGITS
    store
    1.13
     drawer
    1.08
     launcher
    0.98
     store
    0.97
    ortion
    0.97
    Store
    0.94
    reciation
    0.94
    alach
    0.93
     Store
    0.92
    osite
    0.92
    Act Density 0.039%

    No Known Activations