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

    Neuronpedia

    INDEX
    Explanations

    references to proper nouns or terms with special acronyms

    oai_token-act-pair · gpt-3.5-turbo

    words related to animal and plant species, particularly in a scientific or biological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Subtle
    -0.88
     Darling
    -0.82
     Own
    -0.80
     Hurt
    -0.79
     Tracker
    -0.79
     Expend
    -0.78
     Accountability
    -0.78
     Breed
    -0.76
     Lack
    -0.75
     Yard
    -0.75
    POSITIVE LOGITS
    ouses
    0.89
    ensis
    0.88
    otype
    0.87
    ettes
    0.87
    omorph
    0.84
    iculture
    0.84
    oscopic
    0.83
    Äĵ
    0.83
    omial
    0.81
    ahs
    0.81
    Act Density 0.281%

    No Known Activations