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

    mentions of applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deity
    -0.68
     Berm
    -0.68
     Hog
    -0.64
    xual
    -0.63
     cigars
    -0.62
     Protestant
    -0.62
    bilt
    -0.61
     knots
    -0.60
     Deter
    -0.60
     corridors
    -0.57
    POSITIVE LOGITS
    alach
    1.07
    ortion
    1.05
    legate
    1.01
    reciation
    0.99
    earance
    0.93
    osite
    0.93
    store
    0.91
    mable
    0.88
    ointment
    0.88
    ropri
    0.88
    Act Density 0.028%

    No Known Activations