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

    Neuronpedia

    INDEX
    Explanations

    technical terms or jargon, especially related to technology and formal contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.69
     awoken
    -0.67
     rooting
    -0.65
     refrain
    -0.63
    leasing
    -0.62
     volumes
    -0.60
     thence
    -0.59
     reservations
    -0.59
     batches
    -0.59
     seated
    -0.58
    POSITIVE LOGITS
    icians
    1.58
    icol
    1.56
    ically
    1.47
    ological
    1.39
    ologies
    1.30
    iques
    1.27
    ician
    1.26
    icum
    1.21
    ocrat
    1.20
    ocrats
    1.19
    Act Density 0.042%

    No Known Activations