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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships in continuous functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PureComponent
    -0.20
     Cah
    -0.16
     Gra
    -0.15
    jit
    -0.14
    irk
    -0.14
     berg
    -0.14
     berk
    -0.14
     rut
    -0.14
    лож
    -0.14
     Barcl
    -0.13
    POSITIVE LOGITS
     floor
    0.90
    floor
    0.79
     Floor
    0.78
     floors
    0.73
    Floor
    0.72
     roof
    0.71
     ceiling
    0.70
    -floor
    0.69
    _floor
    0.65
     Floors
    0.61
    Act Density 0.175%

    No Known Activations