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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with measuring performance and activities related to physical actions and preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "-ing" suffix

    np_acts-logits-general · gemini-2.0-flash

    actions ending with -ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.89
     beginnetje
    -0.78
     saites
    -0.71
    ScopeManager
    -0.71
    climb
    -0.71
     Climb
    -0.70
    Swim
    -0.69
     Swim
    -0.69
     climb
    -0.67
    swim
    -0.67
    POSITIVE LOGITS
     pinning
    0.79
     drumming
    0.78
     punching
    0.77
     hacking
    0.77
     taping
    0.75
     pumping
    0.75
     patching
    0.74
     stamping
    0.74
     slicing
    0.74
     tagging
    0.74
    Act Density 1.099%

    No Known Activations