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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance or importance of information or actions

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

    "important"

    np_acts-logits-general · gemini-2.0-flash

    important information or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.68
     Fleck
    -0.63
    oblotting
    -0.61
     Gier
    -0.59
     picioare
    -0.54
     Spisak
    -0.54
    secta
    -0.53
     HasFactory
    -0.53
    ecap
    -0.52
    Controllo
    -0.52
    POSITIVE LOGITS
     importance
    1.17
    importance
    1.11
     important
    1.09
     Importance
    1.08
     Important
    1.08
    Importance
    1.05
    Important
    1.02
    important
    0.99
    IMPORTANT
    0.96
     crucial
    0.92
    Act Density 0.168%

    No Known Activations