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

    Neuronpedia

    INDEX
    Explanations

    terms related to sweeping actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¾
    -0.19
    umbo
    -0.18
    ivery
    -0.16
    uby
    -0.15
    uml
    -0.15
    assen
    -0.15
    ubar
    -0.15
    εβ
    -0.15
    halt
    -0.15
    cht
    -0.15
    POSITIVE LOGITS
    stakes
    0.50
     sweep
    0.30
     Swe
    0.30
     swept
    0.28
     Sweep
    0.26
     sweeps
    0.26
     sweeping
    0.25
     aside
    0.24
     away
    0.21
    ingly
    0.21
    Act Density 0.017%

    No Known Activations