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

    Neuronpedia

    INDEX
    Explanations

    statements where credit or acknowledgment is given to someone for a particular achievement or contribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of being credited or recognized for achievements or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shape
    -0.66
     noise
    -0.63
     forms
    -0.63
    Py
    -0.63
     Construct
    -0.61
     sed
    -0.61
    mere
    -0.61
    opia
    -0.61
    grave
    -0.59
    kit
    -0.59
    POSITIVE LOGITS
     credited
    3.88
     attributed
    1.67
     credits
    1.65
     thanked
    1.51
     billed
    1.45
     lauded
    1.44
    redited
    1.39
     credit
    1.37
     blamed
    1.37
     cited
    1.35
    Act Density 0.007%

    No Known Activations