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

    Neuronpedia

    INDEX
    Explanations

    terms related to governance, policies, and administrative actions

    oai_token-act-pair · gpt-3.5-turbo

    connections or relationships between different concepts or elements within a complex context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.77
    amera
    -0.77
    oho
    -0.71
    kees
    -0.69
    raft
    -0.69
     IMAGES
    -0.66
    ibi
    -0.64
    eem
    -0.63
    rily
    -0.63
    wire
    -0.62
    POSITIVE LOGITS
     coupled
    1.25
     consequ
    1.13
     resultant
    0.99
     culminating
    0.95
     resulting
    0.91
     willingness
    0.91
     namely
    0.90
     inability
    0.89
     Flavoring
    0.88
     abandonment
    0.85
    Act Density 0.656%

    No Known Activations