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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical details or specifications

    oai_token-act-pair · gpt-3.5-turbo

    structural elements and relationships within complex topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pling
    -0.72
    lled
    -0.69
    ©
    -0.67
    oping
    -0.66
    gement
    -0.66
    acked
    -0.66
    Org
    -0.65
    ongyang
    -0.65
     Canaver
    -0.64
    elling
    -0.64
    POSITIVE LOGITS
     namely
    0.79
    hetics
    0.70
    including
    0.69
     amen
    0.69
     Including
    0.68
    physical
    0.65
     adject
    0.65
     Firstly
    0.64
     verbal
    0.63
     visual
    0.63
    Act Density 0.386%

    No Known Activations