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

    Neuronpedia

    INDEX
    Explanations

    references to legal and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    juan
    -0.17
    Parms
    -0.17
    addir
    -0.15
    γκο
    -0.15
    aju
    -0.14
    ãĥ¼ãĥ«
    -0.14
    IFORM
    -0.14
    uestion
    -0.14
    argas
    -0.14
    åľį
    -0.14
    POSITIVE LOGITS
     reserves
    0.24
     reserve
    0.24
    reserve
    0.20
     neither
    0.19
     ник
    0.17
     Reserve
    0.16
    onian
    0.16
    commit
    0.16
     Viet
    0.16
    earer
    0.15
    Act Density 0.060%

    No Known Activations