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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duration or continuation of actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "throughout"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.78
    JV
    -0.75
    hl
    -0.70
    Parents
    -0.70
    bol
    -0.70
    nas
    -0.69
    olk
    -0.67
    nery
    -0.65
    rets
    -0.65
    INS
    -0.64
    POSITIVE LOGITS
    eatures
    0.88
     stages
    0.77
     XD
    0.76
    ĸļ
    0.74
     disciplines
    0.71
    ciating
    0.69
     phases
    0.68
     Europe
    0.68
    )=(
    0.68
     Wage
    0.67
    Act Density 0.013%

    No Known Activations