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

    Neuronpedia

    INDEX
    Explanations

    phrases related to softening or lightening concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivar
    -0.16
    enberg
    -0.15
    erras
    -0.15
    urv
    -0.15
    สาร
    -0.15
    allet
    -0.14
    teil
    -0.14
    ãĥ©ãĤ¹
    -0.14
    گرد
    -0.14
    FromClass
    -0.14
    POSITIVE LOGITS
    -than
    0.20
    azor
    0.18
    than
    0.16
    agem
    0.16
    aton
    0.15
    ator
    0.15
     Dean
    0.15
    Dean
    0.15
    atur
    0.14
    å¾ģ
    0.14
    Act Density 0.094%

    No Known Activations