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

    Neuronpedia

    INDEX
    Explanations

    descriptions of personality traits and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.32
     [],
    -0.24
    ा,
    -0.23
    à¥ĩ,
    -0.23
    ++,
    -0.22
    *,
    -0.22
    ®,
    -0.22
    (),
    -0.21
    à¥ĭà¤Ĥ,
    -0.21
    +,
    -0.21
    POSITIVE LOGITS
     but
    0.25
     and
    0.19
    but
    0.18
     sondern
    0.15
     which
    0.14
     etc
    0.14
    and
    0.14
    .and
    0.14
     or
    0.14
     które
    0.14
    Act Density 0.978%

    No Known Activations