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

    Neuronpedia

    INDEX
    Explanations

    expressions and terms related to user engagement and activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.16
    agli
    -0.16
     Vall
    -0.15
    Æł
    -0.15
    üst
    -0.15
    poss
    -0.15
    remaining
    -0.14
    ForEach
    -0.14
    zap
    -0.14
    earned
    -0.14
    POSITIVE LOGITS
    rak
    0.16
    ôte
    0.15
     Drake
    0.15
    oogle
    0.14
     Guild
    0.14
    ordo
    0.14
    lw
    0.14
    nga
    0.14
    kl
    0.14
    imore
    0.14
    Act Density 0.005%

    No Known Activations