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

    Neuronpedia

    INDEX
    Explanations

    descriptions of family members

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships between mothers and their children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.71
    krit
    -0.67
    ript
    -0.65
    met
    -0.63
    Downloadha
    -0.62
    ickr
    -0.62
    esian
    -0.62
    ATIONS
    -0.61
    AE
    -0.60
    bilt
    -0.58
    POSITIVE LOGITS
     twins
    1.08
     slain
    0.88
     daughters
    0.84
     bride
    0.81
     murdered
    0.80
     Trayvon
    0.79
     three
    0.77
     deceased
    0.77
     Sandwich
    0.74
     autistic
    0.73
    Act Density 0.043%

    No Known Activations