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

    Neuronpedia

    INDEX
    Explanations

    terms related to borders and frontiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IContainer
    -0.61
    ConfigureAwait
    -0.56
    ArrowToggle
    -0.54
     colectiva
    -0.51
     tillegg
    -0.51
     visst
    -0.51
     détach
    -0.50
    REFERRED
    -0.50
     אחר
    -0.50
     ruota
    -0.50
    POSITIVE LOGITS
     boundaries
    1.17
     borders
    1.13
     Boundaries
    1.13
     border
    1.03
     boundary
    1.01
     Borders
    0.99
     Boundary
    0.97
    boundaries
    0.97
     BORDER
    0.97
    borders
    0.96
    Act Density 0.034%

    No Known Activations