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

    Neuronpedia

    INDEX
    Explanations

    words related to encouragement or incentives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to promoting or supporting positive actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    çĦ
    -0.76
    ainted
    -0.74
    codes
    -0.70
    amac
    -0.70
    ãĥĺãĥ©
    -0.69
    abase
    -0.69
    ynski
    -0.67
    oland
    -0.67
    ammy
    -0.67
    POSITIVE LOGITS
     entrepreneurship
    1.16
     experimentation
    1.15
     creativity
    1.12
     innovation
    1.06
     participation
    1.02
     curiosity
    1.00
     cooperation
    0.97
     reuse
    0.95
     teamwork
    0.93
     exploration
    0.93
    Act Density 0.123%

    No Known Activations