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

    Neuronpedia

    INDEX
    Explanations

    specific words related to movie details and film release information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iking
    -0.78
    gart
    -0.74
    poke
    -0.74
    onica
    -0.74
    iots
    -0.73
    augh
    -0.72
    acas
    -0.72
    nox
    -0.70
    acus
    -0.68
    instein
    -0.68
    POSITIVE LOGITS
     hence
    1.35
     therefore
    1.34
     consists
    1.26
     consequently
    1.24
     contains
    1.21
     thus
    1.19
     incorporates
    1.16
     includes
    1.15
     secondly
    1.10
     consisted
    1.06
    Act Density 0.522%

    No Known Activations