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

    Neuronpedia

    INDEX
    Explanations

    mentions of spirals or metaphorical downward spirals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different types of spirals and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endment
    -0.79
    Hispanic
    -0.78
    ourke
    -0.78
     Wond
    -0.76
    oral
    -0.75
    arers
    -0.73
    orate
    -0.68
    erity
    -0.67
    ablishment
    -0.67
    ressor
    -0.67
    POSITIVE LOGITS
     spiral
    1.58
     spir
    1.18
     staircase
    1.08
     Spiral
    1.06
     vortex
    0.92
     stair
    0.82
     snowball
    0.78
     erosion
    0.78
     escal
    0.77
     therap
    0.77
    Act Density 0.007%

    No Known Activations