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

    Neuronpedia

    INDEX
    Explanations

    concepts related to communication and setting boundaries within relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĽst
    -0.14
    624
    -0.14
    Intersection
    -0.14
    .gdx
    -0.13
    åĢĴ
    -0.13
    елÑİ
    -0.13
    vara
    -0.13
    anda
    -0.13
    xmm
    -0.13
    eca
    -0.12
    POSITIVE LOGITS
     boundaries
    1.10
     boundary
    1.02
     borders
    0.97
    boundary
    0.83
     Boundary
    0.82
     border
    0.80
     bounds
    0.77
    Boundary
    0.75
     Borders
    0.72
     limits
    0.68
    Act Density 0.277%

    No Known Activations