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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases that denote varying types or categories of information or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Referințe
    -0.43
     recul
    -0.43
     panoramique
    -0.40
    Bakgrunnsstoff
    -0.38
     rétro
    -0.35
     rafters
    -0.35
    孤立
    -0.35
     cusp
    -0.34
     tercio
    -0.34
    delwed
    -0.34
    POSITIVE LOGITS
     somewhere
    1.00
    somewhere
    0.96
    something
    0.93
     Somewhere
    0.93
     somehow
    0.93
     Something
    0.92
    Somewhere
    0.91
     something
    0.90
     Somehow
    0.89
    Something
    0.89
    Act Density 0.442%

    No Known Activations