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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "new" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammers
    -0.78
    WARE
    -0.76
    enance
    -0.72
    isters
    -0.71
    ENTS
    -0.68
    umes
    -0.67
    otto
    -0.67
    lees
    -0.66
    lua
    -0.65
    agree
    -0.65
    POSITIVE LOGITS
    bie
    1.25
    foundland
    1.02
     batch
    0.96
    bies
    0.95
     generation
    0.93
     iteration
    0.86
     edition
    0.84
     testament
    0.81
     wave
    0.80
     dimension
    0.79
    Act Density 0.079%

    No Known Activations