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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to being irritating or bothersome

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "annoy" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardless
    -0.88
    arnaev
    -0.88
    icrobial
    -0.82
    bard
    -0.81
    borg
    -0.81
    ining
    -0.81
    INAL
    -0.78
    etheus
    -0.78
    eval
    -0.76
    icians
    -0.76
    POSITIVE LOGITS
     nuisance
    1.08
     annoy
    1.01
     annoyance
    0.97
     annoying
    0.93
     obnoxious
    0.92
     irritating
    0.85
     inconven
    0.81
     prick
    0.78
     inconvenience
    0.75
     irrit
    0.75
    Act Density 0.025%

    No Known Activations