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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    negative emotions and words associated with failure or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -1.14
    rams
    -0.84
    poons
    -0.83
    fixes
    -0.81
    alks
    -0.81
    icts
    -0.80
    ensions
    -0.79
     profiles
    -0.78
     timelines
    -0.78
    ynski
    -0.76
    POSITIVE LOGITS
     unto
    0.96
     breaker
    0.90
     worth
    0.85
     reel
    0.85
     worthy
    0.81
     compared
    0.79
     nonetheless
    0.79
     affair
    0.79
     akin
    0.76
     starter
    0.75
    Act Density 0.225%

    No Known Activations