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

    Neuronpedia

    INDEX
    Explanations

    the word "multi-" followed by a concept or descriptor

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "multi-" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gleaming
    -0.71
     SPORTS
    -0.70
     Curve
    -0.70
     Ludwig
    -0.67
    IONS
    -0.66
     Wildcats
    -0.66
     Bauer
    -0.65
     Wonderland
    -0.65
     ashes
    -0.65
    姫
    -0.65
    POSITIVE LOGITS
    icult
    0.87
    cro
    0.86
     multi
    0.86
     multit
    0.86
     eyed
    0.85
    multi
    0.85
     multic
    0.83
     sided
    0.82
    absor
    0.81
    urally
    0.81
    Act Density 0.006%

    No Known Activations