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

    Neuronpedia

    INDEX
    Explanations

    phrases related to composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.70
     argint
    -0.66
    TemporalType
    -0.63
     لينك
    -0.63
     cazul
    -0.63
    hlí
    -0.62
    жнему
    -0.60
    quitous
    -0.60
    anggap
    -0.59
     الرياضيه
    -0.59
    POSITIVE LOGITS
     comprised
    1.56
     composed
    1.56
     consists
    1.53
     consisting
    1.51
     consisted
    1.48
     consist
    1.46
    composed
    1.43
     Composed
    1.38
     composée
    1.35
     comprising
    1.30
    Act Density 0.213%

    No Known Activations