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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal values and ethics in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.71
    ########.
    -0.61
     muualla
    -0.55
     cland
    -0.52
    ForTesting
    -0.52
     reopen
    -0.51
     incur
    -0.51
     ReactDOM
    -0.49
    praš
    -0.47
     underwhelming
    -0.47
    POSITIVE LOGITS
    MergeFrom
    0.73
     moral
    0.69
    ettbewer
    0.65
     respect
    0.63
    hdashline
    0.62
     unselfish
    0.62
    abetes
    0.62
     humility
    0.60
     mutual
    0.60
    gdx
    0.60
    Act Density 0.273%

    No Known Activations