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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating logical reasoning or coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptors
    -0.17
    JECTION
    -0.16
    essim
    -0.16
    avian
    -0.15
    shire
    -0.15
    enschaft
    -0.15
    shaw
    -0.15
    ates
    -0.14
    JECT
    -0.14
    lix
    -0.14
    POSITIVE LOGITS
    ://%
    0.15
    ãi
    0.15
    empor
    0.15
    /help
    0.15
    aro
    0.14
    .scalablytyped
    0.14
    erer
    0.14
    bsub
    0.14
     iconName
    0.14
    ëģĶ
    0.14
    Act Density 0.025%

    No Known Activations