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

    Neuronpedia

    INDEX
    Explanations

    mentions of various items or entities across different contexts or situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "various" to indicate diversity or multiple elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vest
    -0.76
    ocene
    -0.73
    O
    -0.69
     ALWAYS
    -0.66
    NN
    -0.65
    onics
    -0.64
    kamp
    -0.64
    cher
    -0.64
     thence
    -0.63
    NER
    -0.63
    POSITIVE LOGITS
    iating
    1.36
     kinds
    1.34
     aspects
    1.12
     sorts
    1.11
     iterations
    1.09
     facets
    1.08
     incarn
    1.05
     types
    1.04
     stages
    1.01
    iates
    1.00
    Act Density 0.028%

    No Known Activations