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

    Neuronpedia

    INDEX
    Explanations

    consecutive words ending in 's'

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UDP
    -0.67
     Provision
    -0.66
     Emer
    -0.64
     Accountability
    -0.64
     Def
    -0.63
     innocence
    -0.62
     Standards
    -0.62
     Fighters
    -0.60
     USA
    -0.60
     Tru
    -0.60
    POSITIVE LOGITS
    alian
    1.03
    abal
    1.02
    senal
    1.01
    ocratic
    1.01
    chy
    1.01
    otropic
    0.99
    ocl
    0.99
    athy
    0.97
    otrop
    0.97
    odic
    0.96
    Act Density 0.162%

    No Known Activations