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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members

    oai_token-act-pair · gpt-3.5-turbo

    references to family members and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DATA
    -0.84
    é¾
    -0.82
    Ni
    -0.80
     Corruption
    -0.79
    Ir
    -0.77
    âķIJ
    -0.72
    ERG
    -0.72
    Cause
    -0.72
    PM
    -0.72
    NL
    -0.71
    POSITIVE LOGITS
    hyde
    0.94
     attendants
    0.91
     counselors
    0.90
     mourning
    0.86
     careg
    0.85
     welf
    0.85
     therap
    0.85
    accompan
    0.84
     grieving
    0.83
     attendant
    0.82
    Act Density 0.330%

    No Known Activations