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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gale
    -0.16
    brook
    -0.15
    nam
    -0.14
    dera
    -0.14
    airs
    -0.14
    bery
    -0.14
     advent
    -0.14
    sex
    -0.14
    /twitter
    -0.14
     Gladiator
    -0.13
    POSITIVE LOGITS
    allen
    0.17
    .OneToOne
    0.15
    اة
    0.15
    atown
    0.15
    toMatch
    0.14
    ocuk
    0.14
    Unload
    0.14
    Äĩe
    0.14
    unsch
    0.14
     perc
    0.14
    Act Density 0.052%

    No Known Activations