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

    Neuronpedia

    INDEX
    Explanations

    hard, solid, tangible objects

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of objects and their interactions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    docs
    -0.70
     Parables
    -0.68
     Childhood
    -0.67
    OND
    -0.65
    alg
    -0.65
    NING
    -0.64
    arten
    -0.64
    clus
    -0.62
    erenn
    -0.62
     continuation
    -0.61
    POSITIVE LOGITS
     resembling
    1.10
     protr
    0.83
    imus
    0.78
     emitting
    0.78
     orbiting
    0.77
     therein
    0.77
     photographed
    0.77
    objects
    0.76
     located
    0.75
     shaped
    0.74
    Act Density 0.243%

    No Known Activations