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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ladder"

    oai_token-act-pair · gpt-3.5-turbo

    references to ladders and their importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    null
    -0.96
     Lies
    -0.79
    asel
    -0.72
     Alic
    -0.72
     Extrem
    -0.66
     frequent
    -0.65
    umn
    -0.63
    gone
    -0.62
    NULL
    -0.62
    panic
    -0.62
    POSITIVE LOGITS
     ladder
    1.40
    pillar
    0.96
     staircase
    0.89
     pige
    0.87
     crane
    0.86
    adders
    0.86
    wcs
    0.84
    pole
    0.83
     stairs
    0.83
    stairs
    0.82
    Act Density 0.010%

    No Known Activations