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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing different aspects of regulations or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.22
     ſind
    -1.16
     photolibrary
    -1.09
     ་་
    -1.06
     crdi
    -1.02
     tfsi
    -1.02
     myſelf
    -1.01
     ―――――
    -1.00
    دانشنامهٔ
    -0.98
     iſt
    -0.96
    POSITIVE LOGITS
    .
    0.85
    ↵↵
    0.82
    "
    0.78
    ↵
    0.76
    -
    0.75
     
    0.74
     The
    0.71
    )
    0.71
      
    0.68
     (
    0.66
    Act Density 1.364%

    No Known Activations