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

    Neuronpedia

    INDEX
    Explanations

    words that indicate personal reflections or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignty
    -0.77
    yethylene
    -0.72
    tellungs
    -0.72
    saraba
    -0.71
     InputDecoration
    -0.68
    ciled
    -0.68
    BibitemShut
    -0.67
    ViewFeatures
    -0.67
    ardless
    -0.67
    orgeous
    -0.67
    POSITIVE LOGITS
    Personensuche
    0.56
    пе
    0.50
    ">//
    0.47
    LookAnd
    0.47
    .*")]
    0.46
     ruch
    0.46
    ⓧ
    0.45
     strop
    0.44
    ._
    0.44
     zwar
    0.44
    Act Density 0.487%

    No Known Activations