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

    Neuronpedia

    INDEX
    Explanations

    expressions of familiarity or personal connection to experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦÏį
    -0.20
     seem
    -0.17
     seems
    -0.17
     lik
    -0.16
     Seems
    -0.15
     seemed
    -0.15
     silence
    -0.14
    enberg
    -0.14
    awe
    -0.14
     seeming
    -0.14
    POSITIVE LOGITS
    arel
    0.17
     somehow
    0.15
     stepped
    0.15
     just
    0.15
    ajaran
    0.15
     someone
    0.14
     barely
    0.14
    alara
    0.14
     Atlas
    0.14
     Lev
    0.14
    Act Density 0.100%

    No Known Activations