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

    Neuronpedia

    INDEX
    Explanations

    queries and phrases related to interaction or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ư
    -0.17
    ÄIJT
    -0.16
    ovah
    -0.16
    اÛĮÛĮ
    -0.15
    arken
    -0.14
     olmadan
    -0.14
    exo
    -0.13
    esser
    -0.13
    iers
    -0.13
     therefore
    -0.13
    POSITIVE LOGITS
     visit
    0.24
     go
    0.23
    better
    0.23
     feel
    0.23
     better
    0.22
    altern
    0.21
     follow
    0.20
     use
    0.20
     via
    0.20
    visit
    0.19
    Act Density 0.083%

    No Known Activations