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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of artistic expression and cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.17
    tero
    -0.15
    ãģ¨ãĤĤ
    -0.15
    ighb
    -0.15
    ega
    -0.15
    omik
    -0.14
    zl
    -0.14
     pragma
    -0.14
    ilir
    -0.14
     haline
    -0.14
    POSITIVE LOGITS
     unless
    0.33
    unless
    0.30
    Unless
    0.26
     Unless
    0.25
     except
    0.25
     alone
    0.24
     exclusively
    0.23
    except
    0.21
    because
    0.20
     saja
    0.20
    Act Density 0.333%

    No Known Activations