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

    Neuronpedia

    INDEX
    Explanations

    mentions of siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to siblings and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umers
    -0.80
    uman
    -0.76
    urate
    -0.74
    olic
    -0.72
    rophe
    -0.70
    olk
    -0.69
    gement
    -0.69
    industrial
    -0.68
    vasive
    -0.68
    olog
    -0.68
    POSITIVE LOGITS
     siblings
    0.98
     adolesc
    0.86
    wcsstore
    0.82
     sibling
    0.80
     Leilan
    0.74
     Inher
    0.71
     Neph
    0.71
    iblings
    0.70
    MpServer
    0.69
     TEAM
    0.67
    Act Density 0.019%

    No Known Activations