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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entanto
    -0.79
    ſelf
    -0.75
    ształ
    -0.73
     myſelf
    -0.68
     themſelves
    -0.68
     ―――――
    -0.68
    BibitemOpen
    -0.68
     négatif
    -0.67
     ――――――――
    -0.67
     itſelf
    -0.67
    POSITIVE LOGITS
    another
    0.79
     another
    0.70
     ANOTHER
    0.68
    Another
    0.61
    tagHelper
    0.61
     Another
    0.59
    astr
    0.58
     grand
    0.56
    WebElementEntity
    0.55
     eines
    0.54
    Act Density 0.093%

    No Known Activations