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

    Neuronpedia

    INDEX
    Explanations

    abstract sections of scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Henson
    -0.77
     pouss
    -0.76
     dgv
    -0.74
     @"/
    -0.72
    IBarButtonItem
    -0.71
    RunWith
    -0.71
    Nino
    -0.70
    loadModel
    -0.70
     setw
    -0.69
    omla
    -0.69
    POSITIVE LOGITS
     abstracts
    1.32
    abstract
    1.25
    Abstract
    1.23
     Abstract
    1.21
     Abstracts
    1.16
     abstract
    1.14
     ABSTRACT
    1.01
    Abstracts
    0.98
     abstracta
    0.96
     abstra
    0.95
    Act Density 0.096%

    No Known Activations