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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and related pronouns in the context of discussions about collective experiences or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jopa
    -0.59
    astify
    -0.58
     nevoie
    -0.56
     subito
    -0.54
     persino
    -0.53
     vocale
    -0.53
     heti
    -0.52
     gånger
    -0.52
     enough
    -0.50
     Enough
    -0.50
    POSITIVE LOGITS
     prepares
    1.14
     nears
    1.02
     prepare
    1.01
     Paglinawan
    0.94
     approaches
    0.91
     progresses
    0.91
     approach
    0.91
     approached
    0.90
     APPROACH
    0.87
     preparing
    0.85
    Act Density 0.181%

    No Known Activations