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

    Neuronpedia

    INDEX
    Explanations

    phrases focused on improvement and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sdk
    -0.16
    .SDK
    -0.15
     Lawson
    -0.15
     fast
    -0.15
    ÅĽcie
    -0.14
    orre
    -0.14
    StateManager
    -0.14
     TORT
    -0.13
     tort
    -0.13
     Polly
    -0.13
    POSITIVE LOGITS
    elas
    0.19
    falls
    0.16
    holm
    0.15
    usi
    0.15
     Contribution
    0.14
    igit
    0.14
    åĩī
    0.14
     Belediyesi
    0.13
    ÙĪÙĬر
    0.13
    akan
    0.13
    Act Density 0.011%

    No Known Activations