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

    Neuronpedia

    INDEX
    Explanations

    discussions around adoption and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .XR
    -0.16
    XD
    -0.15
    аÑĢод
    -0.14
     Laud
    -0.14
    vrier
    -0.14
    ettes
    -0.14
    婦
    -0.14
     nackte
    -0.13
     Fav
    -0.13
    aupt
    -0.13
    POSITIVE LOGITS
     adoption
    0.70
     adopt
    0.68
     Adoption
    0.65
     Adopt
    0.57
     adopted
    0.56
     adopting
    0.53
    adopt
    0.53
     adopts
    0.48
    éĩĩçĶ¨
    0.31
    ADO
    0.28
    Act Density 0.039%

    No Known Activations