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

    Neuronpedia

    INDEX
    Explanations

    phrases related to edits or removals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rem" and its variations with different suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    в
    -0.66
     Labrador
    -0.66
    FP
    -0.64
    REF
    -0.63
     Hath
    -0.60
    gerald
    -0.59
    glers
    -0.59
     Typh
    -0.59
    realDonaldTrump
    -0.58
     climate
    -0.58
    POSITIVE LOGITS
    arkable
    1.32
    nants
    1.28
    nant
    1.23
    ovable
    1.18
    oving
    1.16
    aining
    1.11
    ainers
    1.10
    ittance
    1.04
    arks
    1.02
    edia
    1.00
    Act Density 0.029%

    No Known Activations