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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decision or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asers
    -0.67
    andise
    -0.66
    iser
    -0.63
    tor
    -0.62
    Comments
    -0.62
    itcher
    -0.60
    clip
    -0.60
     meanwhile
    -0.60
     Cheong
    -0.60
    atre
    -0.59
    POSITIVE LOGITS
     happening
    1.03
     raining
    0.99
    nt
    0.94
     impossible
    0.93
     done
    0.87
     okay
    0.86
     meant
    0.85
     gonna
    0.81
     undet
    0.80
     feasible
    0.79
    Act Density 0.341%

    No Known Activations