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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal growth and self-improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal empowerment and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.58
    yssey
    -0.55
     lamented
    -0.54
    ãĥł
    -0.54
     wonder
    -0.54
     stemmed
    -0.52
    ramid
    -0.52
     wondered
    -0.51
    ameless
    -0.51
    except
    -0.51
    POSITIVE LOGITS
     beforehand
    1.16
     sufficiently
    1.01
     enough
    0.99
    enough
    0.90
     correctly
    0.86
    *.
    0.85
     Enough
    0.85
    .(
    0.85
    Enough
    0.85
     properly
    0.84
    Act Density 0.711%

    No Known Activations