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

    Neuronpedia

    INDEX
    Explanations

    supportive statements and expressions of confidence in decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.15
    iske
    -0.15
    ål
    -0.15
    ivot
    -0.14
     Corner
    -0.14
     comfort
    -0.14
     Feed
    -0.13
     emb
    -0.13
    rina
    -0.13
    ough
    -0.13
    POSITIVE LOGITS
     háºŃu
    0.15
    433
    0.15
    435
    0.14
    eros
    0.14
    pis
    0.14
    432
    0.14
    aces
    0.14
    -REAL
    0.14
    gress
    0.14
     anywhere
    0.14
    Act Density 0.248%

    No Known Activations