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

    Neuronpedia

    INDEX
    Explanations

    distance measurements in meters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of distances and measurements in meters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Behavior
    -0.68
     toile
    -0.63
     behav
    -0.63
     slew
    -0.61
    irtual
    -0.60
     fermented
    -0.60
     psycho
    -0.59
    icter
    -0.59
     recre
    -0.57
    lez
    -0.56
    POSITIVE LOGITS
    obiles
    1.12
    umbai
    0.95
    otor
    0.89
    eredith
    0.88
    iles
    0.87
    useum
    0.85
    obil
    0.84
    aiden
    0.83
    ths
    0.81
    otive
    0.81
    Act Density 0.032%

    No Known Activations