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

    Neuronpedia

    INDEX
    Explanations

    terms related to actions involving a significant level of involvement or commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tra" in various contexts, suggesting a focus on the prefix or concept related to "transportation" or "traverse."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mellon
    -0.68
     iod
    -0.67
    ENSE
    -0.66
     Loll
    -0.64
     Mechdragon
    -0.61
    ensable
    -0.61
    maxwell
    -0.60
    heit
    -0.59
     360
    -0.59
    ensor
    -0.59
    POSITIVE LOGITS
    pez
    1.07
    ppings
    0.96
    ph
    0.91
    ordinary
    0.88
    tro
    0.87
     tra
    0.87
    vert
    0.87
    ger
    0.85
    inen
    0.84
    itors
    0.83
    Act Density 0.009%

    No Known Activations