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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familial relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hubby
    -0.16
    .WinForms
    -0.16
    ths
    -0.14
    ÏĢλα
    -0.14
     Husband
    -0.14
    pes
    -0.14
    strup
    -0.14
    oen
    -0.14
     kli
    -0.14
    acia
    -0.14
    POSITIVE LOGITS
     ourselves
    0.18
     himself
    0.18
     friends
    0.18
     myself
    0.18
     herself
    0.17
    .scalablytyped
    0.17
     yourself
    0.16
    UNET
    0.15
     friend
    0.15
    wipe
    0.15
    Act Density 0.041%

    No Known Activations