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

    Neuronpedia

    INDEX
    Explanations

    components related to measurement or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aston
    -0.25
     excell
    -0.25
     marvel
    -0.23
     excellent
    -0.21
     outstanding
    -0.20
     Amazing
    -0.20
     shock
    -0.20
     wonder
    -0.20
     impress
    -0.20
     extraordin
    -0.20
    POSITIVE LOGITS
     noisy
    0.36
     risky
    0.35
     painful
    0.35
     messy
    0.33
     troublesome
    0.33
     costly
    0.33
     restless
    0.32
     aggressive
    0.32
     violent
    0.32
     fierce
    0.31
    Act Density 0.092%

    No Known Activations