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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of gravity

    oai_token-act-pair · gpt-3.5-turbo

    references to gravitational forces and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ointed
    -0.91
    imony
    -0.82
    "]=>
    -0.78
    ts
    -0.77
    ño
    -0.77
    antha
    -0.77
    uterte
    -0.76
     iT
    -0.76
    ership
    -0.76
    ublic
    -0.73
    POSITIVE LOGITS
     gravity
    1.04
     sickness
    0.84
     cooker
    0.82
     perme
    0.82
     equation
    0.78
     anomaly
    0.78
     curv
    0.77
     helium
    0.76
     magnets
    0.76
     distortion
    0.75
    Act Density 0.023%

    No Known Activations