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

    Neuronpedia

    INDEX
    Explanations

    Swedish words related to lightness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports leagues and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.84
     Lazarus
    -0.75
    agons
    -0.72
    Library
    -0.71
    veyard
    -0.70
     McCann
    -0.70
     Tanz
    -0.69
    arger
    -0.69
    amins
    -0.68
     Grimoire
    -0.67
    POSITIVE LOGITS
    thro
    2.52
    lig
    1.90
     thrott
    1.67
     serv
    1.64
     throttle
    1.58
     Thro
    1.39
     fem
    1.36
     idle
    1.31
    buck
    1.24
     rud
    1.21
    Act Density 0.046%

    No Known Activations