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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of longevity or continuity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'lasting' impacts or legacies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffic
    -0.87
    ramid
    -0.86
    ologies
    -0.79
    olog
    -0.79
    alon
    -0.76
    udging
    -0.75
    sing
    -0.75
    umo
    -0.73
    umbn
    -0.72
    plex
    -0.71
    POSITIVE LOGITS
     lasting
    1.18
     veter
    0.89
     adolesc
    0.87
     destro
    0.83
    åĬ
    0.79
    wcs
    0.76
     isot
    0.76
     unden
    0.75
     impact
    0.72
     irreversible
    0.71
    Act Density 0.011%

    No Known Activations