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

    Neuronpedia

    INDEX
    Explanations

    references to force in various contexts

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

    physical forces and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.66
    ⤹
    -0.66
    ductory
    -0.65
    +#+#
    -0.65
    theless
    -0.63
     uLocal
    -0.61
    <unused41>
    -0.59
    <unused52>
    -0.59
    <unused23>
    -0.59
    <unused8>
    -0.59
    POSITIVE LOGITS
     force
    2.09
    force
    1.98
     Force
    1.85
     FORCE
    1.77
    Force
    1.77
    FORCE
    1.53
     forces
    1.35
     Forces
    1.24
    forces
    1.24
     fuerza
    1.22
    Act Density 0.015%

    No Known Activations