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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a contrast between the past and present

    oai_token-act-pair · gpt-3.5-turbo

    references to the past or earlier time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toe
    -0.70
    ting
    -0.68
    mson
    -0.67
    Winged
    -0.65
    ciplinary
    -0.64
    mission
    -0.62
    iliated
    -0.60
     centerpiece
    -0.60
    tted
    -0.59
    ications
    -0.59
    POSITIVE LOGITS
    Ń·
    0.74
    orm
    0.72
    abouts
    0.72
    emort
    0.72
    esar
    0.70
    ratulations
    0.68
    orthy
    0.67
     guiActiveUnfocused
    0.67
    hand
    0.66
    ELL
    0.64
    Act Density 0.040%

    No Known Activations