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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to research findings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LDR
    -0.49
     ज्या
    -0.42
     Remo
    -0.42
     AZ
    -0.41
     Kat
    -0.41
     GenerationType
    -0.39
     Sci
    -0.39
     Blo
    -0.39
     Pred
    -0.39
    Kat
    -0.39
    POSITIVE LOGITS
    makeText
    0.50
    istoitu
    0.47
     enfermed
    0.46
    IntoConstraints
    0.46
    )_/¯
    0.45
     Infór
    0.45
    AutoScale
    0.44
    MessageOf
    0.43
     springfox
    0.43
     artificiales
    0.43
    Act Density 1.516%

    No Known Activations