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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures or objects, particularly related to machinery or architecture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to elevator shafts and references to specific names associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rella
    -0.74
    SEE
    -0.74
    ATHER
    -0.74
     Columb
    -0.71
    bsp
    -0.68
    Dispatch
    -0.68
    guyen
    -0.66
    Nap
    -0.66
     Glenn
    -0.65
     Balt
    -0.65
    POSITIVE LOGITS
     shaft
    1.46
    ials
    0.90
    smanship
    0.80
    stem
    0.79
    wright
    0.77
    nuts
    0.75
    saf
    0.74
    worm
    0.74
    fall
    0.74
    worms
    0.73
    Act Density 0.006%

    No Known Activations