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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and specifications

    oai_token-act-pair · gpt-3.5-turbo

    co-occurrence of conjunctions and phrases indicating connectedness or continuation in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.85
    byss
    -0.75
    opol
    -0.73
    ouk
    -0.72
    ocument
    -0.71
    itor
    -0.71
    oshi
    -0.70
    hower
    -0.70
    icus
    -0.68
    itus
    -0.67
    POSITIVE LOGITS
     ample
    1.22
     plenty
    1.13
     lots
    1.03
     abundant
    1.01
     minimal
    1.00
     lousy
    0.94
     extensive
    0.93
     penchant
    0.93
     excellent
    0.93
     impecc
    0.92
    Act Density 0.359%

    No Known Activations