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

    Neuronpedia

    INDEX
    Explanations

    words related to internet concepts and technologies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "inter" signifying interactions or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.74
    aimon
    -0.70
    \\\\\\\\
    -0.70
    unks
    -0.70
    cffff
    -0.68
    onna
    -0.64
     tremend
    -0.63
    hari
    -0.62
    ccording
    -0.62
     Skydragon
    -0.61
    POSITIVE LOGITS
    mediate
    1.01
    ventions
    0.89
    active
    0.89
    mitt
    0.88
    actively
    0.84
    vention
    0.79
    section
    0.77
    quart
    0.76
    action
    0.75
    mediately
    0.74
    Act Density 0.010%

    No Known Activations