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

    Neuronpedia

    INDEX
    Explanations

    references to spirals

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes related to spirals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourke
    -0.95
    oral
    -0.94
    arers
    -0.93
    alty
    -0.89
    retty
    -0.87
    orate
    -0.82
    uries
    -0.82
    icion
    -0.82
    acl
    -0.82
    orers
    -0.82
    POSITIVE LOGITS
     spiral
    1.41
     staircase
    1.13
     Spiral
    0.98
     rift
    0.86
     stair
    0.86
     spir
    0.79
     vortex
    0.76
     descent
    0.75
     fracture
    0.74
     swirl
    0.69
    Act Density 0.018%

    No Known Activations