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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing future intent or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ize
    -0.16
    çµ
    -0.15
    asant
    -0.15
    anza
    -0.14
    loquent
    -0.14
     synchronization
    -0.14
    ernet
    -0.14
    ogen
    -0.14
    ught
    -0.14
    .nih
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.16
    onna
    0.15
    allis
    0.14
    zcze
    0.14
    ån
    0.14
    prot
    0.14
    inea
    0.13
    çĵ¦
    0.13
     Hao
    0.13
    GetType
    0.13
    Act Density 0.035%

    No Known Activations