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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating knowledge or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igo
    -0.15
    ellery
    -0.15
    StackNavigator
    -0.14
    incare
    -0.14
    ceed
    -0.14
    akens
    -0.14
    irie
    -0.14
    quia
    -0.14
    ware
    -0.14
    ahoma
    -0.14
    POSITIVE LOGITS
     grips
    0.46
     Gri
    0.33
     know
    0.32
    asty
    0.24
     Know
    0.24
     grip
    0.24
     Grip
    0.23
     experience
    0.20
    -know
    0.19
     work
    0.19
    Act Density 0.020%

    No Known Activations