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

    Neuronpedia

    INDEX
    Explanations

    references to physical boundaries and collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.42
    clerview
    -0.42
     Ken
    -0.41
    __((
    -0.41
    loc
    -0.40
     Flip
    -0.39
     Bro
    -0.39
     Att
    -0.39
    liwości
    -0.38
     Conne
    -0.38
    POSITIVE LOGITS
     surla
    0.55
     législ
    0.51
     wall
    0.49
    Walls
    0.48
     dinding
    0.47
     /\.
    0.47
     gräns
    0.47
     boundary
    0.46
     WALL
    0.45
    boundary
    0.43
    Act Density 0.887%

    No Known Activations