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

    Neuronpedia

    INDEX
    Explanations

    terminology related to spheres

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spheres or spherical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -1.05
     Cosponsors
    -0.85
    essee
    -0.80
    ãģĹ
    -0.78
    hiro
    -0.74
    ndra
    -0.74
    ãģĦ
    -0.74
    itors
    -0.72
    ired
    -0.72
    OWN
    -0.69
    POSITIVE LOGITS
     spheres
    0.93
    icular
    0.92
     sphere
    0.86
     Sphere
    0.80
     orb
    0.79
    atform
    0.75
    craft
    0.74
    atoon
    0.73
    fold
    0.72
    bub
    0.71
    Act Density 0.007%

    No Known Activations