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

    Neuronpedia

    INDEX
    Explanations

    words related to generating something, such as power, revenue, and profits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of generating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bull
    -0.75
     TAMADRA
    -0.73
     Velvet
    -0.73
    glass
    -0.73
    tta
    -0.69
     Jess
    -0.69
    fell
    -0.67
    aby
    -0.65
     Sharon
    -0.63
     Hastings
    -0.63
    POSITIVE LOGITS
     generate
    3.20
     generates
    2.44
     generating
    2.31
     generated
    2.28
    generated
    1.86
     Gener
    1.62
     generator
    1.62
     generators
    1.60
    Gener
    1.58
     derive
    1.55
    Act Density 0.022%

    No Known Activations