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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with periods

    oai_token-act-pair · gpt-3.5-turbo

    statements or sentences that denote completion or finalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     malt
    -0.88
     occupation
    -0.85
     numbered
    -0.77
     disappro
    -0.75
    ldom
    -0.74
     sympath
    -0.73
     gloom
    -0.71
    lesiastical
    -0.71
     affili
    -0.71
     profess
    -0.71
    POSITIVE LOGITS
     Moreover
    1.23
     Additionally
    1.22
     Whereas
    1.20
     Furthermore
    1.18
     Users
    1.14
     Instead
    1.13
     Essentially
    1.10
     Unfortunately
    1.08
     Alternatively
    1.07
     Plus
    1.05
    Act Density 0.480%

    No Known Activations