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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of effects and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asaki
    -0.20
    ellas
    -0.16
    ucc
    -0.15
    ullets
    -0.15
    reece
    -0.15
    ruba
    -0.15
    isi
    -0.15
    ร
    -0.15
    atures
    -0.14
    eration
    -0.14
    POSITIVE LOGITS
    uating
    0.22
    uated
    0.21
    iveness
    0.20
    uate
    0.20
    ively
    0.20
    ives
    0.17
    endant
    0.16
    ual
    0.16
    amu
    0.16
    ants
    0.16
    Act Density 0.052%

    No Known Activations