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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antes
    -0.15
    iteur
    -0.14
    å¯
    -0.14
    ãĥ³ãĥĨ
    -0.14
    anning
    -0.14
    CURRENT
    -0.14
    atz
    -0.14
    å¹ħ
    -0.14
    oser
    -0.14
    arga
    -0.14
    POSITIVE LOGITS
     Bowen
    0.15
    sian
    0.15
    estre
    0.15
    pu
    0.14
     instead
    0.14
     Ober
    0.14
     Woodward
    0.14
     Middleton
    0.14
     Hammond
    0.13
    adaki
    0.13
    Act Density 0.050%

    No Known Activations