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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe instances of putting a positive spin on experiences or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loom
    -0.18
    etine
    -0.16
    fold
    -0.16
    etchup
    -0.15
    igh
    -0.15
    541
    -0.15
    zug
    -0.15
    ola
    -0.14
    883
    -0.14
    Fold
    -0.14
    POSITIVE LOGITS
    ulus
    0.16
    ibase
    0.15
    RID
    0.14
     Frontier
    0.14
     anyways
    0.13
     vic
    0.13
    æĹĹ
    0.13
    elier
    0.13
    ulumi
    0.13
    vic
    0.13
    Act Density 0.095%

    No Known Activations