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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving recognition or praise to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to credit, recognition, and praise for achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deadly
    -0.65
     recip
    -0.62
     sho
    -0.61
    afer
    -0.60
    afe
    -0.59
     unpublished
    -0.59
     lookout
    -0.58
     suicidal
    -0.58
     gaping
    -0.58
    WARN
    -0.56
    POSITIVE LOGITS
     bestowed
    0.86
    ability
    0.83
    âĺ
    0.76
     Machina
    0.72
     deserved
    0.72
    thood
    0.71
    enance
    0.69
    DragonMagazine
    0.68
     Tradable
    0.68
    itism
    0.66
    Act Density 0.194%

    No Known Activations