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

    Neuronpedia

    INDEX
    Explanations

    highly descriptive phrases that express emotions or evaluations of movies and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.84
     ModelExpression
    -0.81
    躇
    -0.79
    })));
    -0.76
    seamnă
    -0.71
     typelib
    -0.70
    testens
    -0.67
     betweenstory
    -0.66
     الرياضيه
    -0.65
     виправивши
    -0.64
    POSITIVE LOGITS
     everyone
    0.66
     wonderful
    0.65
     everybody
    0.62
     beautiful
    0.54
     young
    0.52
    1
    0.52
     great
    0.51
     جدًا
    0.50
     Everybody
    0.50
    TagHelpers
    0.49
    Act Density 0.229%

    No Known Activations