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

    Neuronpedia

    INDEX
    Explanations

    words related to perception and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.16
    ynchronously
    -0.15
    illo
    -0.14
    ãĥ¬ãĥ¼
    -0.14
    ики
    -0.13
    aje
    -0.13
    exus
    -0.13
    ubo
    -0.13
    aret
    -0.12
    ucch
    -0.12
    POSITIVE LOGITS
     themselves
    0.30
     himself
    0.25
     herself
    0.23
    phas
    0.21
     ourselves
    0.21
     myself
    0.20
     thems
    0.20
     oneself
    0.18
     it
    0.18
     Äijây
    0.18
    Act Density 0.144%

    No Known Activations