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

    Neuronpedia

    INDEX
    Explanations

    words related to specific professions or occupations

    oai_token-act-pair · gpt-3.5-turbo

    specific cultural and social references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.58
     Lesbian
    -0.55
    Thumbnail
    -0.55
    uana
    -0.55
    vous
    -0.53
    endment
    -0.50
     Ern
    -0.50
     Appears
    -0.47
     Emerging
    -0.47
     Municip
    -0.47
    POSITIVE LOGITS
    isively
    0.64
    ishly
    0.60
    pes
    0.59
    heartedly
    0.58
    bugs
    0.57
    ograms
    0.55
     immunity
    0.54
     buffs
    0.54
    bol
    0.54
    actively
    0.54
    Act Density 1.687%

    No Known Activations