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

    Neuronpedia

    INDEX
    Explanations

    words related to cleaning and maintenance tasks

    oai_token-act-pair · gpt-3.5-turbo

    actions and movements related to people and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Correct
    -0.62
     âĹı
    -0.61
    emi
    -0.60
     Compass
    -0.58
     predecessor
    -0.57
    closure
    -0.56
     Structure
    -0.56
    TION
    -0.55
    avier
    -0.55
     Scale
    -0.55
    POSITIVE LOGITS
     endlessly
    0.95
     passers
    0.93
     piles
    0.89
     endless
    0.87
     frantically
    0.87
     throats
    0.85
     frantic
    0.83
     hordes
    0.82
     incess
    0.81
     beds
    0.80
    Act Density 1.092%

    No Known Activations