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

    Neuronpedia

    INDEX
    Explanations

    topics related to social dynamics and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.16
    ufen
    -0.16
    æĭ¬
    -0.15
    lical
    -0.15
    WEEN
    -0.15
     ADVISED
    -0.14
    ogle
    -0.14
    anko
    -0.14
    é¨
    -0.14
    lico
    -0.13
    POSITIVE LOGITS
     whom
    0.38
     nearby
    0.34
     around
    0.28
     who
    0.26
     near
    0.25
     close
    0.24
    near
    0.23
     similarly
    0.22
    around
    0.21
     nearest
    0.20
    Act Density 0.183%

    No Known Activations