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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation and observers' opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    observers' thoughts and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.54
    httphttps
    -0.49
    SequentialGroup
    -0.49
    ſelves
    -0.47
    󠁣
    -0.46
    SPATH
    -0.45
     فريبيس
    -0.44
     eſt
    -0.43
    (;;)
    -0.43
    UnsafeEnabled
    -0.42
    POSITIVE LOGITS
     detra
    0.44
     viewers
    0.44
     hopes
    0.43
     everybody
    0.42
     observers
    0.42
    ViewImports
    0.41
     hope
    0.41
     onlookers
    0.40
     admirers
    0.40
     expectations
    0.40
    Act Density 0.020%

    No Known Activations