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

    Neuronpedia

    INDEX
    Explanations

    references related to caves and underground features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.67
    endphp
    -0.63
    taxia
    -0.58
     Grazing
    -0.56
     grazing
    -0.56
     windmill
    -0.55
     patrols
    -0.55
     graze
    -0.54
     checkpoints
    -0.54
     pastures
    -0.53
    POSITIVE LOGITS
     rooms
    0.91
     room
    0.85
     Inside
    0.85
     inside
    0.84
    Inside
    0.82
     Rooms
    0.82
    Rooms
    0.80
     cave
    0.78
     cavern
    0.78
     enclosed
    0.74
    Act Density 0.306%

    No Known Activations