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

    Neuronpedia

    INDEX
    Explanations

    descriptions of criminal or confrontational incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    genre
    -0.74
     historically
    -0.70
     galaxy
    -0.66
    zbollah
    -0.66
    industrial
    -0.66
     nonpartisan
    -0.65
     ecosystem
    -0.65
     asteroid
    -0.64
     peripheral
    -0.64
     kindred
    -0.64
    POSITIVE LOGITS
     Afterwards
    1.33
    Later
    1.31
    Eventually
    1.29
     proceeded
    1.26
    Then
    1.24
     Then
    1.21
    sequently
    1.21
     Eventually
    1.19
    Soon
    1.19
    then
    1.18
    Act Density 5.265%

    No Known Activations