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

    Neuronpedia

    INDEX
    Explanations

    references to research results or outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fone
    -0.52
     réguli
    -0.50
     Erschein
    -0.50
    ämme
    -0.48
     التالية
    -0.48
    נצ
    -0.47
     jauh
    -0.47
    🔽
    -0.47
    原因
    -0.47
    väg
    -0.47
    POSITIVE LOGITS
    tonsoft
    0.78
     AssemblyCulture
    0.78
    trise
    0.71
     Supra
    0.65
    __(/*!
    0.62
    Tikang
    0.61
     Bourgoin
    0.60
     sherds
    0.60
    říve
    0.59
    ंदीखरीदारी
    0.59
    Act Density 0.012%

    No Known Activations