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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orris
    -0.16
    sak
    -0.15
    idth
    -0.15
    ạc
    -0.15
    .mdl
    -0.15
    >Title
    -0.14
    uento
    -0.14
    akte
    -0.14
    ãģĭãĤĬ
    -0.14
    787
    -0.14
    POSITIVE LOGITS
     ::
    0.17
    .topic
    0.16
     Framework
    0.15
     Frontier
    0.15
    Framework
    0.14
    Environment
    0.14
    Topic
    0.14
    croft
    0.14
    Alpha
    0.14
     MERCHANTABILITY
    0.14
    Act Density 0.001%

    No Known Activations