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

    Neuronpedia

    INDEX
    Explanations

    criticisms and negative sentiments in the text

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions or phrases that convey a sense of addition or layering of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortmund
    -0.84
     Deaths
    -0.82
    wic
    -0.81
    EStream
    -0.80
    SHIP
    -0.78
    ulkan
    -0.76
    ETS
    -0.75
    AGES
    -0.74
    ulia
    -0.74
    YING
    -0.74
    POSITIVE LOGITS
     therefore
    1.07
     unpredictable
    1.02
     thus
    1.01
     prone
    1.00
     adventurous
    1.00
     hence
    0.96
     efficient
    0.95
     predictable
    0.95
     devoid
    0.93
     fragile
    0.93
    Act Density 0.151%

    No Known Activations