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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving frequency or repetition tied to the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heastern
    -0.73
    borgh
    -0.70
    estial
    -0.67
    hirt
    -0.66
    ractive
    -0.64
    estic
    -0.62
    ewitness
    -0.61
    rily
    -0.60
    mand
    -0.60
    SourceFile
    -0.57
    POSITIVE LOGITS
    activity
    0.95
    efficiency
    0.89
    between
    0.81
    effic
    0.78
    clus
    0.77
     advance
    0.76
     captivity
    0.74
    escap
    0.73
     vain
    0.73
    appropriate
    0.73
    Act Density 0.155%

    No Known Activations