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

    Neuronpedia

    INDEX
    Explanations

    concepts related to guarantees and certainty in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alone
    -0.17
     Stanton
    -0.15
    alone
    -0.15
    -alone
    -0.14
     Alone
    -0.14
    vala
    -0.14
    gether
    -0.14
    orc
    -0.14
    orce
    -0.14
    ippers
    -0.14
    POSITIVE LOGITS
     equally
    0.18
    PLICIT
    0.16
    SSIP
    0.16
    tent
    0.15
    iage
    0.15
    abela
    0.14
    \OptionsResolver
    0.14
    noop
    0.14
    tpl
    0.14
     worse
    0.14
    Act Density 0.325%

    No Known Activations