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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something negatively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "terrible" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.99
    ership
    -0.92
    illary
    -0.84
    cript
    -0.82
    ilus
    -0.82
    adr
    -0.81
    illance
    -0.81
    paio
    -0.80
    ipel
    -0.80
    sterdam
    -0.80
    POSITIVE LOGITS
     earthqu
    1.03
     awful
    0.99
     terrible
    0.97
     horrible
    0.94
     nightmare
    0.94
     nightmares
    0.93
     conflic
    0.92
     havoc
    0.89
     headache
    0.87
     dreadful
    0.82
    Act Density 0.010%

    No Known Activations