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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuity or repetition

    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
    GE
    -0.71
    Reviewer
    -0.71
    JV
    -0.70
    potion
    -0.68
    LS
    -0.68
    INS
    -0.68
    bol
    -0.67
    umo
    -0.66
    GH
    -0.66
    ND
    -0.66
    POSITIVE LOGITS
    eatures
    0.85
     disciplines
    0.79
     stages
    0.77
     phases
    0.73
    ciating
    0.69
    ĸļ
    0.69
     intermedi
    0.67
     Europe
    0.66
    atform
    0.65
     continents
    0.64
    Act Density 0.022%

    No Known Activations