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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison and equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inya
    -0.15
    itra
    -0.15
    ering
    -0.15
    swer
    -0.15
    UFF
    -0.15
    afone
    -0.14
    appa
    -0.14
    antee
    -0.14
    uff
    -0.14
    ãĥĵãĥ¼
    -0.14
    POSITIVE LOGITS
     maybe
    0.44
    maybe
    0.40
    çĶļèĩ³
    0.35
     possibly
    0.32
     Maybe
    0.32
    Maybe
    0.31
    ä¹ĥ
    0.31
     perhaps
    0.30
     indeed
    0.28
     vielleicht
    0.28
    Act Density 0.157%

    No Known Activations