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

    Neuronpedia

    INDEX
    Explanations

    technical terms or phrases related to digital technology and processes

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and transitional phrases in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.84
    thora
    -0.79
    agically
    -0.76
    ubes
    -0.71
    andals
    -0.69
    azel
    -0.69
    izens
    -0.68
    aced
    -0.67
    azeera
    -0.67
    ãĤĵ
    -0.65
    POSITIVE LOGITS
     whereby
    1.77
     meaning
    1.43
     wherein
    1.41
     which
    1.31
     aka
    1.29
    which
    1.15
     namely
    1.13
     ie
    1.13
    meaning
    1.07
     where
    1.01
    Act Density 0.379%

    No Known Activations