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

    Neuronpedia

    INDEX
    Explanations

    biographical details about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     safer
    -0.55
     kasarigan
    -0.51
     allAfrica
    -0.50
    Risks
    -0.50
     safe
    -0.50
     easier
    -0.50
     skippy
    -0.50
     quicker
    -0.49
     risk
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
    Rhestr
    0.38
     feveral
    0.36
    invokeLater
    0.35
    {@
    0.34
    曾
    0.33
    Παραπομπές
    0.32
    ɵɵelementStart
    0.32
    ########.
    0.32
     entend
    0.31
     inscriptions
    0.31
    Act Density 0.073%

    No Known Activations