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

    Neuronpedia

    INDEX
    Explanations

    expressions of visibility and acknowledgment of actions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reputation
    -0.19
     reputation
    -0.15
     anonymity
    -0.15
    anyak
    -0.14
    isper
    -0.14
    nika
    -0.14
     reput
    -0.14
    ruba
    -0.14
    ilha
    -0.14
     fame
    -0.14
    POSITIVE LOGITS
     signs
    0.33
     Signs
    0.30
     initiative
    0.23
     leadership
    0.22
     symptoms
    0.21
     prowess
    0.19
     interest
    0.19
    boat
    0.19
     improvement
    0.19
     evidence
    0.19
    Act Density 0.085%

    No Known Activations