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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public statements or comments

    oai_token-act-pair · gpt-3.5-turbo

    statements or remarks made by individuals in positions of authority or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ource
    -0.72
    oen
    -0.65
    rollment
    -0.64
    ioxide
    -0.63
    ertain
    -0.63
    vari
    -0.60
    eers
    -0.60
     Currently
    -0.60
    properties
    -0.59
    ric
    -0.59
    POSITIVE LOGITS
     fateful
    0.84
     memorable
    0.69
     aftermath
    0.66
    rompt
    0.64
    ï¸
    0.63
    æµ
    0.63
     transpired
    0.62
     botched
    0.61
     Charlottesville
    0.60
    Thumbnail
    0.60
    Act Density 0.859%

    No Known Activations