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

    Neuronpedia

    INDEX
    Explanations

    references to architectural features, particularly ceilings and lighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.71
    NegativeButton
    -0.61
     slip
    -0.54
    slip
    -0.53
     StatelessWidget
    -0.53
     scrub
    -0.53
     Wallflower
    -0.53
    ++];
    -0.53
    rinfo
    -0.49
     Curl
    -0.49
    POSITIVE LOGITS
     skies
    0.94
     sopra
    0.88
     sky
    0.87
     skys
    0.87
     Sky
    0.85
     Skies
    0.84
     roofs
    0.83
     Skys
    0.83
     SKY
    0.82
     roof
    0.82
    Act Density 0.236%

    No Known Activations