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

    Neuronpedia

    INDEX
    Explanations

    mentions of the force of gravity

    oai_token-act-pair · gpt-3.5-turbo

    references to gravitational forces or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ointed
    -0.85
    imony
    -0.83
    ten
    -0.77
    "]=>
    -0.76
    uterte
    -0.76
    ts
    -0.76
    ership
    -0.74
    ublic
    -0.73
     iT
    -0.72
    nam
    -0.71
    POSITIVE LOGITS
     gravity
    1.13
     helium
    0.88
     anomaly
    0.86
     sickness
    0.85
    gravity
    0.85
     distortion
    0.83
     cooker
    0.82
     Gravity
    0.81
     curv
    0.81
     acceleration
    0.81
    Act Density 0.019%

    No Known Activations